DeepSeek v4

626

iimpact_sy about 4 hours ago 309 commentsRead Article on api-docs.deepseek.com

ZH version is available. Content is displayed in original English for accuracy.

https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main...

⚡ Community Insights

Discussion Sentiment

83% Positive

Analyzed from 7094 words in the discussion.

Discussion (309 Comments)Read Original on HackerNews

jari_mustonen•39 minutes ago

Open Source as it gets in this space, top notch developer documentation, and prices insanely low, while delivering frontier model capabilities. So basically, this is from hackers to hackers. Loving it!

Also, note that there's zero CUDA dependency. It runs entirely on Huawei chips. In other words, Chinese ecosystem has delivered a complete AI stack. Like it or not, that's a big news. But what's there not to like when monopolies break down?

ifwinterco•18 minutes ago

As a Brit I'm here for it to be honest, I'm tired of America with everything that's going on.

China is not perfect but a bit of competition is healthy and needed

sudo_cowsay•11 minutes ago

I sometimes wonder if there are any security risks with using Chinese LLMs. Is there?

slekker•34 minutes ago

But remember to not ask about Taiwan!

Lionga•6 minutes ago

Quit a bit better then made to bomb little girl schools in Iran.

spiderfarmer•11 minutes ago

Just ask it for a summary of the USA’s role in Iran, Gaza, Lebanon and its recent threats against Panama, Cuba and Greenland! It might be able to keep track.

throwa356262•about 1 hour ago

Seriously, why can't huge companies like OpenAI and Google produce documentation that is half this good??

https://api-docs.deepseek.com/guides/thinking_mode

No BS, just a concise description of exactly what I need to write my own agent.

lykr0n•38 minutes ago

It's because they're optimizing for a different problem.

Western Models are optimizing to be used as an interchangeable product. Chinese models are being optimizing to be built upon.

raincole•35 minutes ago

> Western Models are optimizing to be used as an interchangeable product

Why? It sounds like the stupidest idea ever. Interchangeability = no lock-in = no moot.

peepee1982•23 minutes ago

If you want other people to know whether you're being genuine or sarcastic, you'll have to put a bit more effort into your comments. Your comment just adds noise.

kubb•6 minutes ago

Western orgs have been captured by Silicon Valley style patrimonialism, and aren’t based on merit anymore.

vitorgrs•38 minutes ago

Meanwhile, they don't actually say which model you are running on Deepseek Chat website.

Alifatisk•about 1 hour ago

You might enjoy Z.ais api docs aswell

orbital-decay•38 minutes ago

>we implement end-to-end, bitwise batch-invariant, and deterministic kernels with minimal performance overhead

Pretty cool, I think they're the first to guarantee determinism with the fixed seed or at the temperature 0. Google came close but never guaranteed it AFAIK. DeepSeek show their roots - it may not strictly be a SotA model, but there's a ton of low-level optimizations nobody else pays attention to.

revolvingthrow•about 2 hours ago

> pricing "Pro" $3.48 / 1M output tokens vs $4.40

I’d like somebody to explain to me how the endless comments of "bleeding edge labs are subsidizing the inference at an insane rate" make sense in light of a humongous model like v4 pro being $4 per 1M. I’d bet even the subscriptions are profitable, much less the API prices.

edit: $1.74/M input $3.48/M output on OpenRouter

schneehertz•about 1 hour ago

This price is high even because of the current shortage of inference cards available to DeepSeek; they claimed in their press release that once the Ascend 950 computing cards are launched in the second half of the year, the price of the Pro version will drop significantly

Bombthecat•11 minutes ago

In six month deepseek won't be sota anymore und usage will be wayyyy down.

menzoic•9 minutes ago

API prices may be profitable. Subscriptions may still be subsidized for power users. Free tiers almost certainly are. And frontier labs may be subsidizing overall business growth, training, product features, and peak capacity, even if a normal metered API call is profitable on marginal inference.

amunozo•25 minutes ago

I was thinking the same. How can it be than other providers can offer third-party open source models with roughly the similar quality like this, Kimi K2.6 or GLM 5.1 for 10 times less the price? How can it be that GPT 5.5 is suddenly twice the price as GPT 5.4 while being faster? I don't believe that it's a bigger, more expensive model to run, it's just they're starting to raise up the prices because they can and their product is good (which is honest as long as they're transparent with it). Honestly the movement about subscription costing the company 20 times more than we're paying is just a PR movement to justify the price hike.

peepee1982•12 minutes ago

I'm pretty sure OpenAI and Anthropic are overpricing their token billed API usage mainly as an incentive to commit to get their subscriptions instead.

m00x•about 1 hour ago

They are profitable to opex costs, but not capex costs with the current depreciation schedules, though those are now edging higher than expected.

vitorgrs•32 minutes ago

And they actually say the prices will be "significantly" lower in second semester when Huawei 650 chips comes in.

jimmydoe•29 minutes ago

They’ve also announced Pro price will further drop 2H26 once they have more HUAWEI chips.

mirzap•about 1 hour ago

My thoughts exactly. I also believe that subscription services are profitable, and the talk about subsidies is just a way to extract higher profit margins from the API prices businesses pay.

Bombthecat•9 minutes ago

Google stated a while back, that with tpus they are able to sell at cost / with profit.

Aka: everyone who uses Nvidia isn't selling at cost, because Nvidia is so expensive.

dminik•32 minutes ago

I mean, not one "bleeding edge" lab has stated they are profitable. They don't publish financials aside from revenue. And in Anthropic's case, they fuck with pricing every week. Clearly something is wrong here.

raincole•about 1 hour ago

Insert always has been meme.

But seriously, it just stems from the fact some people want AI to go away. If you set your conclusion first, you can very easily derive any premise. AI must go away -> AI must be a bad business -> AI must be losing money.

zarzavat•about 1 hour ago

Before the AI bubble that will burst any time now, there was the AI winter that would magically arrive before the models got good enough to rival humans.

masafej536•about 1 hour ago

Point taken but there isnt any western providers there yet. Power is cheaper in china.

NitpickLawyer•about 1 hour ago

As this is a new arch with tons of optimisations, it'll take some time for inference engines to support it properly, and we'll see more 3rd party providers offer it. Once that settles we'll have a median price for an optimised 1.6T model, and can "guesstimate" from there what the big labs can reasonably serve for the same price. But yeah, it's been said for a while that big labs are ok on API costs. The only unknown is if subscriptions were profitable or not. They've all been reducing the limits lately it seems.

3uler•about 1 hour ago

These models are open and there are tons of western providers offering it at comparable rates.

sekai•42 minutes ago

> I’d like somebody to explain to me how the endless comments of "bleeding edge labs are subsidizing the inference at an insane rate" make sense in light of a humongous model like v4 pro being $4 per 1M. I’d bet even the subscriptions are profitable, much less the API prices.

One answer - Chinese Communist Party. They are being subsidized by the state.

primaprashant•about 1 hour ago

While SWE-bench Verified is not a perfect benchmark for coding, AFAIK, this is the first open-weights model that has crossed the threshold of 80% score on this by scoring 80.6%.

Back in Nov 2025, Opus 4.5 (80.9%) was the first proprietary model to do so.

fblp•about 3 hours ago

There's something heartwarming about the developer docs being released before the flashy press release.

onchainintel•about 3 hours ago

Insert obligatory "this is the way" Mando scene. Indeed!

necovek•about 3 hours ago

Where's the training data and training scripts since you are calling this open source?

Edit: it seems "open source" was edited out of the parent comment.

b65e8bee43c2ed0•about 2 hours ago

doesn't it get tiring after a while? using the same (perceived) gotcha, over and over again, for three years now?

no one is ever going to release their training data because it contains every copyrighted work in existence. everyone, even the hecking-wholesome safety-first Anthropic, is using copyrighted data without permission to train their models. there you go.

necovek•about 1 hour ago

There is an easy fix already in widespread use: "open weights".

It is very much a valuable thing already, no need to taint it with wrong promise.

Though I disagree about being used if it was indeed open source: I might not do it inside my home lab today, but at least Qwen and DeepSeek would use and build on what eg. Facebook was doing with Llama, and they might be pushing the open weights model frontier forward faster.

Tepix•33 minutes ago

Nvidia did with Nemo.

fragmede•about 2 hours ago

it's not a gotcha but people using words in ways others don't like.

bl4ckneon•about 1 hour ago

Aww yes, let me push a couple petabytes to my git repo for everyone to download...

necovek•about 1 hour ago

An easier thing would be to say "open weights", yes.

0-_-0•about 1 hour ago

Weights are the source, training data is the compiler.

injidup•about 1 hour ago

You got it the wrong way round. It's more akin to.

1. Training data is the source. 2. Training is compilation/compression. 3. Weights are the compiled source akin to optimized assembly.

However it's an imperfect analogy on so many levels. Nitpick away.

sidcool•about 3 hours ago

Truly open source coming from China. This is heartwarming. I know if the potential ulterior motives.

b65e8bee43c2ed0•about 1 hour ago

American companies want a scan of your asshole for the privilege of paying to access their models, and unapologetically admit to storing, analyzing, training on, and freely giving your data to any authorities if requested. Chinese ulteriority is hypothetical, American is blatant.

thesmtsolver2•4 minutes ago

As someone with Tibetan friends and as someone from India, Chinese ulterior motives are way more clear.

elefanten•about 1 hour ago

It’s not remotely hypothetical you’d have to be living under a rock to believe that. And the fusion with a one-party state government that doesn’t tolerate huge swathes of thoughtspace being freely discussed is completely streamlined, not mediated by any guardrails or accountability.

This “no harm to me” meme about a foreign totalitarian government (with plenty of incentive to run influence ops on foreigners) hoovering your data is just so mind-bogglingly naive.

ben_w•about 1 hour ago

As a non-American, everything you wrote other than "one party" applies to the current US regime.

Relatively speaking, DeepSeek is less untrustworthy than Grok.

When I try ChatGPT on current events from the White House it interprets them as strange hypotheticals rather than news, which is probably more a problem with DC than with GPT, but whatever.

randomNumber7•12 minutes ago

The USA has one of the highest percentages of their population in prison.

Even for minor stuff like beeing addicted to drugs.

Looks pretty totalitarian to me.

oceanplexian•38 minutes ago

> And the fusion with a one-party state government that doesn’t tolerate huge swathes of thoughtspace being freely discussed

That would be a great argument if the American models weren’t so heavily censored.

The Chinese model might dodge a question if I ask it about 1-2 specific Chinese cultural issues but then it also doesn’t moralize me at every turn because I asked it to use a piece of security software.

danny_codes•about 1 hour ago

It’s an open model? So you can run it yourself if you want to

b65e8bee43c2ed0•25 minutes ago

>This “no harm to me” meme about a foreign totalitarian government (with plenty of incentive to run influence ops on foreigners) hoovering your data is just so mind-bogglingly naive.

yes, this is exactly what I'm saying.

theshackleford•about 1 hour ago

> This “no harm to me” meme about a foreign totalitarian government (with plenty of incentive to run influence ops on foreigners) hoovering your data is just so mind-bogglingly naive.

This is why I’ve been urging everyone I know to move away from American based services and providers. It’s slow but honest work.

t0lo•about 1 hour ago

And you're saying Americans aren't banned from criticising their elites?

Quothling•23 minutes ago

It's a little sad that tech now comes down to geopolitics, but if you're not in the USA then what is the difference? I'm Danish, would I rather give my data to China or to a country which recently threatened the kingdom I live in with military invasion? Ideally I'd give them to Mistral, but in reality we're probably going to continue building multi-model tools to make sure we share our data with everyone equally.

spaceman_2020•39 minutes ago

I don’t care about whatever “ulterior motives” they might have

My country’s per capita income is $2500 a year. We can’t pay perpetual rent to OAI/Anthropic

djyde•20 minutes ago

Same

try-working•about 2 hours ago

if you want to understand why labs open source their models: http://try.works/why-chinese-ai-labs-went-open-and-will-rema...

wraptile•about 1 hour ago

> Internet comments say that open sourcing is a national strategy, a loss maker subsidized by the government. On the contrary, it is a commercial strategy and the best strategy available in this industry.

This sounds whole lot like potatoh potahto. I think the former argument is very much the correct one: China can undercut everyone and win, even at a loss. Happened with solar panels, steel, evs, sea food - it's a well tested strategy and it works really well despite the many flavors it comes in.

That being said a job well done for the wrong reasons is still a job well done so we should very much welcome these contributions, and maybe it's good to upset western big tech a bit so it's remains competitive.

try-working•22 minutes ago

It is not only that Chinese labs can undercut on price. It is that they must. They must give away their models for free by open sourcing them, and they must even give away free inference services for people to try them. That is the point of the post.

I_am_tiberius•about 3 hours ago

Open weight!

alecco•about 2 hours ago

Please don't slander the most open AI company in the world. Even more open than some non-profit labs from universities. DeepSeek is famous for publishing everything. They might take a bit to publish source code but it's almost always there. And their papers are extremely pro-social to help the broader open AI community. This is why they struggle getting funded because investors hate openness. And in China they struggle against the political and hiring power of the big tech companies.

Just this week they published a serious foundational library for LLMs https://github.com/deepseek-ai/TileKernels

Others worth mentioning:

https://github.com/deepseek-ai/DeepGEMM a competitive foundational library

https://github.com/deepseek-ai/Engram

https://github.com/deepseek-ai/DeepSeek-V3

https://github.com/deepseek-ai/DeepSeek-R1

https://github.com/deepseek-ai/DeepSeek-OCR-2

They have 33 repos and counting: https://github.com/orgs/deepseek-ai/repositories?type=all

And DeepSeek often has very cool new approaches to AI copied by the rest. Many others copied their tech. And some of those have 10x or 100x the GPU training budget and that's their moat to stay competitive.

The models from Chinese Big Tech and some of the small ones are open weights only. (and allegedly benchmaxxed) (see https://xcancel.com/N8Programs/status/2044408755790508113). Not the same.

kortilla•6 minutes ago

It’s not slander to say something true. These are open weights, not open source. They don’t provide the training data or the methodology requires to reproduce these weights.

So you can’t see what facts are pruned out, what biases were applied, etc. Even more importantly, you can’t make a slightly improved version.

This model is as open source as a windows XP installation ISO.

patshead•about 1 hour ago

DeepSeek's models are indeed open weight. Why do you feel that pointing this out would be considered slander?

0-_-0•about 1 hour ago

Weights are the source, training data is the compiler

crazylogger•about 1 hour ago

Training data == source code, training algorithm == compiler, model weights == compiled binary.

ngruhn•29 minutes ago

isn't it more like the data is the source, the training process is the compiler, and the weights are the binary output.

yanis_t•about 3 hours ago

Already on Openrouter. Pro version is $1.74/m/input, $3.48/m/output, while flash $0.14/m/input, 0.28/m/output.

astrod•about 2 hours ago

Getting 'Api Error' here :( Every other model is working fine.

poglet•about 2 hours ago

Try interacting with it through the website, it will give an error and some explanation on the issue. I had to relax my guardrail settings.

esafak•about 2 hours ago

https://openrouter.ai/deepseek/deepseek-v4-pro

https://openrouter.ai/deepseek/deepseek-v4-flash

77ko•about 2 hours ago

Its on OR - but currently not available on their anthropic endpoint. OR if you read this, pls enable it there! I am using kimi-2.6 with Claude Code, works well, but Deepseek V4 gives an error:

`https://openrouter.ai/api/messages with model=deepseek/deepseek-v4-pro, OR returns an error because their Anthropic-compat translator doesn't cover V4 yet. The Claude CLI dutifully surfaces that error as "model...does not exist"

sho•15 minutes ago

So, this is the version that's able to serve inference from Huawei chips, although it was still trained on nVidia. So unless I'm very much mistaken this is the biggest and best model yet served on (sort of) readily-available chinese-native tech. Performance and stability will be interesting to see; openrouter currently saying about 1.12s and 30tps, which isn't wonderful but it's day one after all.

In other words, things are hotting up in the GPU war!

mchusma•about 3 hours ago

For comparison on openrouter DeepSeek v4 Flash is slightly cheaper than Gemma 4 31b, more expensive than Gemma 4 26b, but it does support prompt caching, which means for some applications it will be the cheapest. Excited to see how it compares with Gemma 4.

MillionOClock•30 minutes ago

I wonder why there aren't more open weights model with support for prompt caching on OpenRouter.

gbnwl•about 3 hours ago

I’m deeply interested and invested in the field but I could really use a support group for people burnt out from trying to keep up with everything. I feel like we’ve already long since passed the point where we need AI to help us keep up with advancements in AI.

satvikpendem•about 2 hours ago

Don't keep up. Much like with news, you'll know when you need to know, because someone else will tell you first.

wordpad•about 3 hours ago

The players barely ever change. People don't have problems following sports, you shouldn't struggle so much with this once you accept top spot changes.

gbnwl•about 2 hours ago

I didn't express this well but my interest isn't "who is in the top spot", and is more _why and _how various labs get the results they do. This is also magnified by the fact that I'm not only interested in hosted providers of inference but local models as well. What's your take on the best model to run for coding on 24GB of VRAM locally after the last few weeks of releases? Which harness do you prefer? What quants do you think are best? To use your sports metaphor it's more than following the national leagues but also following college and even high school leagues as well. And the real interest isn't even who's doing well but WHY, at each level.

renticulous•about 1 hour ago

Follow the AI newsletters. They bundle the news along with their Op-Ed and summarize it better.

ehnto•about 3 hours ago

It is funny seeing people ping pong between Anthropic and ChatGPT, with similar rhetoric in both directions.

At this point I would just pick the one who's "ethics" and user experience you prefer. The difference in performance between these releases has had no impact on the meaningful work one can do with them, unless perhaps they are on the fringes in some domain.

Personally I am trying out the open models cloud hosted, since I am not interested in being rug pulled by the big two providers. They have come a long way, and for all the work I actually trust to an LLM they seem to be sufficient.

DiscourseFan•about 2 hours ago

I find ChatGPT annoying mostly

vrganj•about 2 hours ago

It honestly has all kinda felt like more of the same ever since maybe GPT4?

New model comes out, has some nice benchmarks, but the subjective experience of actually using it stays the same. Nothing's really blown my mind since.

Feels like the field has stagnated to a point where only the enthusiasts care.

ifwinterco•9 minutes ago

For coding Opus 4.5 in q3 2025 was still the best model I've used.

Since then it's just been a cycle of the old model being progressively lobotomised and a "new" one coming out that if you're lucky might be as good as the OG Opus 4.5 for a couple of weeks.

Subjective but as far as I can tell no progress in almost a year, which is a lifetime in 2022-25 LLM timelines

trueno•about 2 hours ago

holy shit im right there with you

seanobannon•about 3 hours ago

Weights available here: https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro

BoorishBears•about 2 hours ago

https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-Base https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-Base

And we got new base models, wonderful, truly wonderful

yanis_t•15 minutes ago

Is there a harness that is as good as cloud code that can be used with open weight models?

sixhobbits•14 minutes ago

Try pi coding agent!

nthypes•about 3 hours ago

https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main...

Model was released and it's amazing. Frontier level (better than Opus 4.6) at a fraction of the cost.

0xbadcafebee•about 3 hours ago

I don't think we need to compare models to Opus anymore. Opus users don't care about other models, as they're convinced Opus will be better forever. And non-Opus users don't want the expense, lock-in or limits.

As a non-Opus user, I'll continue to use the cheapest fastest models that get my job done, which (for me anyway) is still MiniMax M2.5. I occasionally try a newer, more expensive model, and I get the same results. I have a feeling we might all be getting swindled by the whole AI industry with benchmarks that just make it look like everything's improving.

versteegen•about 2 hours ago

Which model's best depends on how you use it. There's a huge difference in behaviour between Claude and GPT and other models which makes some poor substitutes for others in certain use cases. I think the GPT models are a bad substitute for Claude ones for tasks such as pair-programming (where you want to see the CoT and have immediate responses) and writing code that you actually want to read and edit yourself, as opposed to just letting GPT run in the background to produce working code that you won't inspect. Yes, GPT 5.4 is cheap and brilliant but very black-box and often very slow IME. GPT-5.4 still seems to behave the same as 5.1, which includes problems like: doesn't show useful thoughts, can think for half an hour, says "Preparing the patch now" then thinks for another 20 min, gives no impression of what it's doing, reads microscopic parts of source files and misses context, will do anything to pass the tests including patching libraries...

ind-igo•about 2 hours ago

Agree with your assessment, I think after models reached around Opus 4.5 level, its been almost indistinguishable for most tasks. Intelligence has been commoditized, what's important now is the workflows, prompting, and context management. And that is unique to each model.

vidarh•17 minutes ago

Same for me. There are tasks when I want the smartest model. But for a whole lot of tasks I now default to Sonnet, or go with cheaper models like GLM, Kimi, Qwen. DeepSeek hasn't been in the mix for a while because their previous model had started lagging, but will definitely test this one again.

The tricky part is that the "number of tokens to good result" does absolutely vary, and you need a decent harness to make it work without too much manual intervention, so figuring out which model is most cost-effective for which tasks is becoming increasingly hard, but several are cost-effective enough.

wuschel•43 minutes ago

This is not true for some cases e.g. there are stark differences in the correctness of answers in certain type of case work.

spaceman_2020•38 minutes ago

I found Opus 4.7 to be actually worse than Opus 4.6 for my use case

Substantially worse at following instructions and overoptimized for maximizing token usage

sandos•about 1 hour ago

Is Opus nerfed somehow in Copilot? Ive tried it numerous times, it has never reallt woved me. They seem to have awfully small context windows, but still. Its mostly their reasoning which has been off

Codex is just so much better, or the genera GPT models.

specproc•12 minutes ago

Opus just got killed in Copilot. I always found it great, FWIW.

https://github.blog/news-insights/company-news/changes-to-gi...

kmarc•about 2 hours ago

This resonates with me a lot.

I do some stuff with gemini flash and Aider, but mostly because I want to avoid locking myself into a walled garden of models, UIs and company

post-it•about 2 hours ago

What do you run these on? I've gotten comfortable with Claude but if folks are getting Opus performance for cheaper I'll switch.

oceanplexian•about 1 hour ago

You can just use Claude Code with a few env vars, most of these providers offer an Anthropic compatible API

slopinthebag•about 2 hours ago

Try Charm Crush first, it's a native binary. If it's unbearable, try opencode, just with the knowledge your system will probably be pwned soon since it's JS + NPM + vibe coding + some of the most insufferable devs in the industry behind that product.

If you're feeling frisky, Zed has a decent agent harness and a very good editor.

sandGorgon•about 1 hour ago

actually this is not the reason - the harness is significantly better. There is no comparable harness to Claude Code with skills, etc.

Opencode was getting there, but it seems the founders lost interest. Pi could be it, but its very focused on OpenClaw. Even Codex cli doesnt have all of it.

which harness works well with Deepseek v4 ?

darkwater•about 1 hour ago

What's the issue with OC? I tried it a bit over 2 months ago, when I was still on Claude API, and it actually liked more that CC (i.e. the right sidebar with the plan and a tendency at asking less "security" questions that CC). Why is it so bad nowadays?

avereveard•about 1 hour ago

eh idk. until yesterday opus was the one that got spatial reasoning right (had to do some head pose stuff, neither glm 5.1 nor codex 5.3 could "get" it) and codex 5.3 was my champion at making UX work.

So while I agree mixed model is the way to go, opus is still my workhorse.

onchainintel•about 3 hours ago

How does it compare to Opus 4.7? I've been immersed in 4.7 all week participating in the Anthropic Opus 4.7 hackathon and it's pretty impressive even if it's ravenous from a token perspective compared to 4.6

greenknight•about 3 hours ago

The thing is, it doesnt need to beat 4.7. it just needs to do somewhat well against it.

This is free... as in you can download it, run it on your systems and finetune it to be the way you want it to be.

libraryofbabel•about 1 hour ago

> you can download it, run it on your systems

In theory, sure, but as other have pointed out you need to spend half a million on GPUs just to get enough VRAM to fit a single instance of the model. And you’d better make sure your use case makes full 24/7 use of all that rapidly-depreciating hardware you just spent all your money on, otherwise your actual cost per token will be much higher than you think.

In practice you will get better value from just buying tokens from a third party whose business is hosting open weight models as efficiently as possible and who make full use of their hardware. Even with the small margin they charge on top you will still come out ahead.

p1esk•about 3 hours ago

Do you think a lot of people have “systems” to run a 1.6T model?

onchainintel•about 3 hours ago

Completely agree, not suggesting it needs ot just genuinely curious. Love that it can be run locally though. Open source LLMs punching back pretty hard against proprietary ones in the cloud lately in terms of performance.

kelseyfrog•about 3 hours ago

What's the hardware cost to running it?

johnmaguire•about 3 hours ago

... if you have 800 GB of VRAM free.

spaceman_2020•37 minutes ago

Tbh I was more productive with 4.6 than ever before and if AI progress locks in permanently at 4.6 tier, I’d be pretty happy

rvz•about 3 hours ago

It is more than good enough and has effectively caught up with Opus 4.6 and GPT 5.4 according to the benchmarks.

It's about 2 months behind GPT 5.5 and Opus 4.7.

As long as it is cheap to run for the hosting providers and it is frontier level, it is a very competitive model and impressive against the others. I give it 2 years maximum for consumer hardware to run models that are 500B - 800B quantized on their machines.

It should be obvious now why Anthropic really doesn't want you to run local models on your machine.

deaux•about 2 hours ago

Vibes > Benchmarks. And it's all so task-specific. Gemini 3 has scored very well in benchmarks for very long but is poor at agentic usecases. A lot of people prefering Opus 4.6 to 4.7 for coding despite benchmarks, much more than I've seen before (4.5->4.6, 4->4.5).

Doesn't mean Deepseek v4 isn't great, just benchmarks alone aren't enough to tell.

snovv_crash•about 2 hours ago

With the ability of the Qwen3.6 27B, I think in 2 years consumers will be running models of this capability on current hardware.

colordrops•about 3 hours ago

What's going to change in 2 years that would allow users to run 500B-800B parameter models on consumer hardware?

doctoboggan•about 3 hours ago

Is it honestly better than Opus 4.6 or just benchmaxxed? Have you done any coding with an agent harness using it?

If its coding abilities are better than Claude Code with Opus 4.6 then I will definitely be switching to this model.

bokkies•about 1 hour ago

Apparently glm5.1 and qwen coder latest is as good as opus 4.6 on benchmarks. So I tried both seriously for a week (glm Pro using CC) and qwen using qwen companion. Thought I could save $80 a month. Unfortunately after 2 days I had switched back to Max. The speed (slower on both although qwen is much faster) and errors (stupid layout mistakes, inserting 2 footers then refusing to remove one, not seeing obvious problems in screenshots & major f-ups of functionality), not being able to view URLs properly, etc. I'll give deepseek a go but I suspect it will be similar. The model is only half the story. Also been testing gpt5.4 with codex and it is very almost as good as CC... better on long running tasks running in background. Not keen on ChatGPT codex 'personality' so will stick to CC for the most part.

madagang•about 3 hours ago

Their Chinese announcement says that, based on internal employee testing, it is not as good as Opus 4.6 Thinking, but is slightly better than Opus 4.6 without Thinking enabled.

mchusma•about 3 hours ago

I appreciate this, makes me trust it more than benchmarks.

ibic•about 2 hours ago

In case people wonder where the announcement is (you can easily translate it via browser if you don't read Chinese): https://mp.weixin.qq.com/s/8bxXqS2R8Fx5-1TLDBiEDg

It's still a "preview" version atm.

deaux•about 2 hours ago

That's super interesting, isn't Deepseek in China banned from using Anthropic models? Yet here they're comparing it in terms of internal employee testing.

bbor•about 3 hours ago

For the curious, I did some napkin math on their posted benchmarks and it racks up 20.1 percentage point difference across the 20 metrics where both were scored, for an average improvement of about 2% (non-pp). I really can't decide if that's mind blowing or boring?

Claude4.6 was almost 10pp better at at answering questions from long contexts ("corpuses" in CorpusQA and "multiround conversations" in MRCR), while DSv4 was a staggering 14pp better at one math challenge (IMOAnswerBench) and 12pp better at basic Q&A (SimpleQA-Verified).

Quasimarion•about 2 hours ago

FWIW it's also like 10x cheaper.

NitpickLawyer•about 3 hours ago

> (better than Opus 4.6)

There we go again :) It seems we have a release each day claiming that. What's weird is that even deepseek doesn't claim it's better than opus w/ thinking. No idea why you'd say that but anyway.

Dsv3 was a good model. Not benchmaxxed at all, it was pretty stable where it was. Did well on tasks that were ood for benchmarks, even if it was behind SotA.

This seems to be similar. Behind SotA, but not by much, and at a much lower price. The big one is being served (by ds themselves now, more providers will come and we'll see the median price) at 1.74$ in / 3.48$ out / 0.14$ cache. Really cheap for what it offers.

The small one is at 0.14$ in / 0.28$ out / 0.028$ cache, which is pretty much "too cheap to matter". This will be what people can run realistically "at home", and should be a contender for things like haiku/gemini-flash, if it can deliver at those levels.

slopinthebag•about 2 hours ago

Anthropic fans would claim God itself is behind Opus by 3-6 months and then willingly be abused by Boris and one of his gaslighting tweets.

LMAO

NitpickLawyer•about 2 hours ago

> Anthropic fans ...

I have no idea why you'd think that, but this is straight from their announcement here (https://mp.weixin.qq.com/s/8bxXqS2R8Fx5-1TLDBiEDg):

> According to evaluation feedback, its user experience is better than Sonnet 4.5, and its delivery quality is close to Opus 4.6's non-thinking mode, but there is still a certain gap compared to Opus 4.6's thinking mode.

This is the model creators saying it, not me.

sergiotapia•about 3 hours ago

The dragon awakes yet again!

kindkang2024•about 3 hours ago

There appears a flight of dragons without heads. Good fortune.

That's literally what the I Ching calls "good fortune."

Competition, when no single dragon monopolizes the sky, brings fortune for all.

rapind•about 3 hours ago

Pop?

amunozo•20 minutes ago

For those who rely on open source models but don't want to stop using frontier models, how do you manage it? Do you pay any of the Chinese subscription plans? Do you pay the API directly? After GPT 5.5 release, however good it is, I am a bit tired of this price hiking and reduced quota every week. I am now unemployed and cannot afford more expensive plans for the moment.

aquir•32 minutes ago

It is great! I asked the question what I always ask of new models ("what would Ian M Banks think about the current state of AI") and it gave me a brilliant answer! Funny enough the answer contained multiple criticisms of his own creators ("Chinese state entities", "Social Credit System").

sixhobbits•14 minutes ago

I know people don't like Twitter links here but the main link just goes to their main docs site generic 'getting started' page.

The website now has a link to the announcement on Twitter here https://x.com/deepseek_ai/status/2047516922263285776

Copying text of that below

DeepSeek-V4 Preview is officially live & open-sourced! Welcome to the era of cost-effective 1M context length.

DeepSeek-V4-Pro: 1.6T total / 49B active params. Performance rivaling the world's top closed-source models.

DeepSeek-V4-Flash: 284B total / 13B active params. Your fast, efficient, and economical choice.

Try it now at http://chat.deepseek.com via Expert Mode / Instant Mode. API is updated & available today!

Tech Report: https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main...

Open Weights: https://huggingface.co/collections/deepseek-ai/deepseek-v4

zkmon•about 1 hour ago

They released 1.6 T pro base model on huggingface. First time I'm seeing a "T" model here.

Imanari•about 1 hour ago

Just tested it via openrounter in the Pi Coding agent and it regularly fails to use the read and write tool correctly, very disappointing. Anyone know a fix besides prompting "always use the provided tools instead of writing your own call"

abstracthinking•about 1 hour ago

They have just released it, give it some time, they probably haven't pretested it with Pi

Imanari•about 1 hour ago

How can they fix it after the release? They would have to retrain/finetune it further, no?

zargon•about 1 hour ago

It's only in preview right now. And anyway, yes, models regularly get updated training.

But in this case, it's more likely just to be a tooling issue.

coderssh•34 minutes ago

Feels like the real story here is cost/performance tradeoff rather than raw capability. Benchmarks keep moving incrementally, but efficiency gains like this actually change who can afford to build on top.

zargon•about 3 hours ago

The Flash version is 284B A13B in mixed FP8 / FP4 and the full native precision weights total approximately 154 GB. KV cache is said to take 10% as much space as V3. This looks very accessible for people running "large" local models. It's a nice follow up to the Gemma 4 and Qwen3.5 small local models.

sbinnee•about 3 hours ago

Price is appealing to me. I have been using gemini 3 flash mainly for chat. I may give it a try.

input: $0.14/$0.28 (whereas gemini $0.5/$3)

Does anyone know why output prices have such a big gap?

girvo•about 1 hour ago

Output is what the compute is used for above all else; costs more hardware time basically than prompt processing (input) which is a lot faster

tokenmaxxinej•about 1 hour ago

input tokens are processed at 10-50 times the speed of output tokens since you can process then in batches and not one at a time like output tokens

CJefferson•about 2 hours ago

What's the current best framework to have a 'claude code' like experience with Deepseek (or in general, an open-source model), if I wanted to play?

deaux•about 1 hour ago

https://pi.dev/

TranquilMarmot•about 2 hours ago

https://opencode.ai/

Alifatisk•42 minutes ago

You can use CC with other models, you aren’t forced to use Claude model.

whoopdeepoo•about 2 hours ago

You can use deepseek with Claude code

esperent•42 minutes ago

You can, but does it work well? I assume CC has all kinds of Claude specific prompts in it, wouldn't you be better with a harness designed to be model agnostic like pi.dev or OpenCode?

0x142857•about 2 hours ago

claude-code-cli/opencode/codex

cztomsik•18 minutes ago

So is this the first AI lab using MUON for their frontier model?

hodgehog11•15 minutes ago

No, Muon was developed by Moonshot; they've been using it in their Kimi models since Kimi K2 in 2025.

simonw•about 3 hours ago

I like the pelican I got out of deepseek-v4-flash more than the one I got from deepseek-v4-pro.

https://simonwillison.net/2026/Apr/24/deepseek-v4/

Both generated using OpenRouter.

For comparison, here's what I got from DeepSeek 3.2 back in December: https://simonwillison.net/2025/Dec/1/deepseek-v32/

And DeepSeek 3.1 in August: https://simonwillison.net/2025/Aug/22/deepseek-31/

And DeepSeek v3-0324 in March last year: https://simonwillison.net/2025/Mar/24/deepseek/

torginus•about 1 hour ago

This is just a random thought, but have you tried doing an 'agentic' pelican?

As in have the model consider its generated SVG, and gradually refine it, using its knowledge of the relative positions and proportions of the shapes generated, and have it spin for a while, and hopefully the end result will be better than just oneshotting it.

Or maybe going even one step further - most modern models have tool use and image recognition capabilities - what if you have it generate an SVG (or parts/layers of it, as per the model's discretion) and feed it back to itself via image recognition, and then improve on the result.

I think it'd be interesting to see, as for a lot of models, their oneshot capability in coding is not necessarily corellated with their in-harness ability, the latter which really matters.

simonw•25 minutes ago

I tried that for the GPT-5 launch - a self-improving loop that renders the SVG, looks at it and tries again - and the results were surprisingly disappointing.

I should try it again with the more recent models.

JSR_FDED•about 3 hours ago

No way. The Pro pelican is fatter, has a customized front fork, and the sun is shining! He’s definitely living the best life.

chronogram•about 1 hour ago

The pro pelican is a work of art! It goes dimensions that no other LLM has gone before.

w4yai•about 3 hours ago

yeah. look at these 4 feathers (?) on his bum too.

oliver236•about 2 hours ago

a lot of dumplings

nickvec•about 3 hours ago

The Flash one is pretty impressive. Might be my favorite so far in the pelican-riding-a-bicycle series

murkt•about 2 hours ago

DeepSeek pelicans are the angriest pelicans I’ve seen so far.

kristopolous•about 2 hours ago

they're just late for work.

lazycatjumping•33 minutes ago

996 Pelican, lol

mikae1•about 2 hours ago

Being a bicycle geometry nerd I always look at the bicycle first.

Let me tell you how much the Pro one sucks... It looks like failed Pedersen[1]. The rear wheel intersects with the bottom bracket, so it wouldn't even roll. Or rather, this bike couldn't exist.

The flash one looks surprisingly correct with some wild fork offset and the slackest of seat tubes. It's got some lowrider[2] aspirations with the small wheels, but with longer, Rivendellish[3], chainstays. The seat post has different angle than the seat tube, so good luck lowering that.

[1] https://en.wikipedia.org/wiki/Pedersen_bicycle

[2] https://en.wikipedia.org/wiki/Lowrider_bicycle

[3] https://www.rivbike.com/

simonw•about 2 hours ago

This is an excellent comment. Thanks for this - I've only ever thought about whether the frame is the right shape, I never thought about how different illustrations might map to different bicycle categories.

mikae1•about 2 hours ago

Some other reactions:

I wonder which model will try some more common spoke lacing patterns. Right now there seems to be a preference for radial lacing, which is not super common (but simple to draw). The Flash and Pro one uses 16 spoke rims, which actually exist[1] but are not super common.

The Pro model fails badly at the spokes. Heck, the spokes sit on the outside of the drive side of the rim and tire. Have a nice ride riding on the spokes (instead of the tire) welded to the side of your rim.

Both bikes have the drive side on the left, which is very very uncommon. That can't exist in the training data.

[1] https://cicli-berlinetta.com/product/campagnolo-shamal-16-sp...

jojobas•about 2 hours ago

The Pedersen looks like someone failed the "draw a bicycle" test and decided to adjust the universe.

catelm•about 2 hours ago

I think the pelican on a bike is known widely enough that of seizes to be useful as a benchmark. There is even a pelican briefly appearing in the promo video of GPT-5, if I'm not mistaken https://openai.com/gpt-5/. So the companies are apparently aware of it.

simonw•23 minutes ago

It was a bigger deal in the Gemini 3.1 launch: https://x.com/JeffDean/status/2024525132266688757

nsoonhui•about 1 hour ago

To me this is the perfect proof that

1) LLM is not AGI. Because surely if AGI it would imply that pro would do better than flash?

2) and because of the above, Pelican example is most likely already being benchmaxxed.

chvid•about 1 hour ago

Is it then Deepseek hosted by Deepseek?

How much does the drawing change if you ask it again?

brutal_chaos_•about 2 hours ago

What was your prompt for the image? Apologies if this should be obvious.

shawn_w•about 2 hours ago

>Generate an SVG of a pelican riding a bicycle

at the top of the linked pages.

ycui1986•about 2 hours ago

I really like the pro version. The pelican is so cute.

theanonymousone•about 2 hours ago

Where is the GPT 5.5 Pelican?

simonw•22 minutes ago

https://news.ycombinator.com/item?id=47879092#47880421

culopatin•about 1 hour ago

In the 5.5 topic

lobochrome•about 2 hours ago

Why they so angry?

EnPissant•about 1 hour ago

This should not be the top comment on every model release post. It's getting tiring.

blitzar•about 1 hour ago

This should be the bottom comment on the pelican comment on every model release post.

EnPissant•about 1 hour ago

Clearly the top comment should be "Imagine a beowulf cluster of Deepseek v4!"

bandrami•about 1 hour ago

I don't mind that High Flyer completely ripped off Anthropic to do this so much as I mind that they very obviously waited long enough for the GAB to add several dozen xz-level easter eggs to it.

gardnr•about 2 hours ago

865 GB: I am going to need a bigger GPU.

rohanm93•about 2 hours ago

This is shockingly cheap for a near frontier model. This is insane.

For context, for an agent we're working on, we're using 5-mini, which is $2/1m tokens. This is $0.30/1m tokens. And it's Opus 4.6 level - this can't be real.

I am uncomfortable about sending user data which may contain PII to their servers in China so I won't be using this as appealing as it sounds. I need this to come to a US-hosted environment at an equivalent price.

Hosting this on my own + renting GPUs is much more expensive than DeepSeek's quoted price, so not an option.

esperent•39 minutes ago

> I am uncomfortable about sending user data which may contain PII to their servers in China

As a European I feel deeply uncomfortable about sending data to US companies where I know for sure that the government has access to it.

I also feel uncomfortable sending it to China.

If you'd asked me ten years ago which one made me more uncomfortable. China.

But now I'm not so sure, in fact I'm starting to lean towards the US as being the major risk.

fractalf•about 1 hour ago

Right now Im much more worried about sending data to the US and A.. At least theres a less chanse it will be missused against -me-

Aliabid94•about 3 hours ago

MMLU-Pro:

Gemini-3.1-Pro at 91.0

Opus-4.6 at 89.1

GPT-5.4, Kimi2.6, and DS-V4-Pro tied at 87.5

Pretty impressive

ant6n•about 2 hours ago

Funny how Gemini is theoretically the best -- but in practice all the bugs in the interface mean I don't want to use it anymore. The worst is it forgets context (and lies about it), but it's very unreliable at reading pdfs (and lies about it). There's also no branch, so once the context is lost/polluted, you have to start projects over and build up the context from scratch again.

spaceman_2020•34 minutes ago

The sheer number of bugs and lack of meaningful improvements in Google products is a clear counterargument to the AI bull thesis

If AI was so good at coding, why can’t it actually make a usable Gemini/AI Studio app?

lazycatjumping•31 minutes ago

I gave up on Gemini 3.1 Pro in VSCode after 2 hours. They fully refunded me.

esperent•37 minutes ago

Yeah if I could use Gemini with pi.dev that would be my choice. But Gemini CLI is just so, so bad.

donbreo•7 minutes ago

Aaaand it cant still name all the states in India,or say what happened in 1989

jessepcc•about 3 hours ago

At this point 'frontier model release' is a monthly cadence, Kimi 2.6 Claude 4.6 GPT 5.5, the interesting question is which evals will still be meaningful in 6 months.

xnx•about 1 hour ago

Such different time now than early 2025 when people thought Deepaeek was going to kill the market for Nvidia.

Ifkaluva•35 minutes ago

They might still kill the market for NVIDIA, if future releases prioritize Huawei chips

storus•about 2 hours ago

Oh well, I should have bought 2x 512GB RAM MacStudios, not just one :(

jdeng•about 3 hours ago

Excited that the long awaited v4 is finally out. But feel sad that it's not multimodal native.

apexalpha•about 1 hour ago

This FLash model might be affordable for OpenClaw. I run it on my mac 48gb ram now but it's slowish.

clark1013•about 2 hours ago

Looking forward to DeepSeek Coding Plan

m_abdelfattah•about 1 hour ago

I came here to say the same :) !

sibellavia•about 2 hours ago

A few hours after GPT5.5 is wild. Can’t wait to try it.

taosx•about 3 hours ago

MErge? https://news.ycombinator.com/item?id=47885014

luyu_wu•about 4 hours ago

For those who didn't check the page yet, it just links to the API docs being updated with the upcoming models, not the actual model release.

talim•about 3 hours ago

Weights are on Huggingface FWIW. https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/tree/main

cmrdporcupine•about 3 hours ago

My submission here https://news.ycombinator.com/item?id=47885014 done at the same time was to the weights.

dang, probably the two should be merged and that be the link

culi•about 3 hours ago

there's no pinging. Someone's gotta email dang

tariky•about 2 hours ago

Anyone tried with make web UI with it? How good is it? For me opus is only worth because of it.

tcbrah•about 1 hour ago

giving meta a run for its money, esp when it was supposed to be the poster child for OSS models. deepseek is really overshadowing them rn

KaoruAoiShiho•about 3 hours ago

SOTA MRCR (or would've been a few hours earlier... beaten by 5.5), I've long thought of this as the most important non-agentic benchmark, so this is especially impressive. Beats Opus 4.7 here

WhereIsTheTruth•about 1 hour ago

Interesting note:

"Due to constraints in high-end compute capacity, the current service capacity for Pro is very limited. After the 950 supernodes are launched at scale in the second half of this year, the price of Pro is expected to be reduced significantly."

So it's going to be even cheaper

jfxia•36 minutes ago

Is V4 still not a multi-modal model?

vitorgrs•26 minutes ago

Not yet... Which is a shame.

reenorap•about 3 hours ago

Which version fits in a Mac Studio M3 Ultra 512 GB?

simonw•about 3 hours ago

The Flash one should - it's 160GB on Hugging Face: https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash/tree/ma...

ycui1986•about 2 hours ago

So, dual RTX PRO 6000

gigatexal•30 minutes ago

Has anyone used it? How does it compare to gpt 5.5 or opus 4.7?

augment_me•43 minutes ago

Amaze amaze amaze

aliljet•about 3 hours ago

How can you reasonably try to get near frontier (even at all tps) on hardware you own? Maybe under 5k in cost?

revolvingthrow•about 2 hours ago

For flash? 4 bit quant, 2x 96GB gpu (fast and expensive) or 1x 96GB gpu + 128GB ram (still expensive but probably usable, if you’re patient).

A mac with 256 GB memory would run it but be very slow, and so would be a 256GB ram + cheapo GPU desktop, unless you leave it running overnight.

The big model? Forget it, not this decade. You can theoretically load from SSD but waiting for the reply will be a religious experience.

Realistically the biggest models you can run on local-as-in-worth-buying-as-a-person hardware are between 120B and 200B, depending on how far you’re willing to go on quantization. Even this is fairly expensive, and that’s before RAM went to the moon.

zargon•about 2 hours ago

Flash is less than 160 GB. No need to quantize to fit in 2x 96 GB. Not sure how much context fits in 30 GB, but it should be a good amount.

redrove•about 1 hour ago

It seems to be 160GB at mixed FP4+FP8 precision, FYI. Full FP8 is 250GB+. (B)F16 at around double I would assume.

zozbot234•about 1 hour ago

Run on an old HEDT platform with a lot of parallel attached storage (probably PCIe 4) and fetch weights from SSD. You'd ultimately be limited by the latency of these per-layer fetches, since MoE weights are small. You could reduce the latencies further by buying cheap Optane memory on the second-hand market.

awakeasleep•about 2 hours ago

The same way you fit a bucket wheel excavator in your garage

floam•about 2 hours ago

Very carefully

datadrivenangel•about 2 hours ago

A loaded macbook pro can get you to the frontier from 24 months ago at ~10-40tok/s, which is plenty fast enough for regular chatting.

542458•about 2 hours ago

The low end could be something like an eBay-sourced server with a truckload of DDR3 ram doing all-cpu inference - secondhand server models with a terabyte of ram can be had for about 1.5K. The TPS will be absolute garbage and it will sound like a jet engine, but it will nominally run.

The flash version here is 284B A13B, so it might perform OK with a fairly small amount of VRAM for the active params and all regular ram for the other params, but I’d have to see benchmarks. If it turns out that works alright, an eBay server plus a 3090 might be the bang-for-buck champ for about $2.5K (assuming you’re starting from zero).

jdoe1337halo•about 2 hours ago

More like 500k

mariopt•about 2 hours ago

Does deepseek has any coding plan?

jeffzys8•about 2 hours ago

swrrt•about 3 hours ago

Any visualised benchmark/scoreboard for comparison between latest models? DeepSeek v4 and GPT-5.5 seems to be ground breaking.

rvz•about 3 hours ago

The paper is here: [0]

Was expecting that the release would be this month [1], since everyone forgot about it and not reading the papers they were releasing and 7 days later here we have it.

One of the key points of this model to look at is the optimization that DeepSeek made with the residual design of the neural network architecture of the LLM, which is manifold-constrained hyper-connections (mHC) which is from this paper [2], which makes this possible to efficiently train it, especially with its hybrid attention mechanism designed for this.

There was not that much discussion around it some months ago here [3] about it but again this is a recommended read of the paper.

I wouldn't trust the benchmarks directly, but would wait for others to try it for themselves to see if it matches the performance of frontier models.

Either way, this is why Anthropic wants to ban open weight models and I cannot wait for the quantized versions to release momentarily.

[0] https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main...

[1] https://news.ycombinator.com/item?id=47793880

[2] https://arxiv.org/abs/2512.24880

[3] https://news.ycombinator.com/item?id=46452172

jeswin•about 3 hours ago

> this is why Anthropic wants to ban open weight models

Do you have a source?

louiereederson•about 2 hours ago

More like he wants to ban accelerator chip sales to China, which may be about “national security” or self preservation against a different model for AI development which also happens to be an existential threat to Anthropic. Maybe those alternatives are actually one and the same to him.

namegulf•about 3 hours ago

Is there a Quantized version of this?

luew•about 2 hours ago

We will be hosting it soon at getlilac.com!

coolThingsFirst•37 minutes ago

I got an API key without credit card details I didn’t know they had a free plan.

sergiotapia•about 2 hours ago

Using it with opencode sometimes it generates commands like:

    bash({"command":"gh pr create --title "Improve Calendar module docs and clean up idiomatic Elixir" --body "$(cat <<'EOF'
    Problem
    The Calendar modu...

like generating output, but not actually running the bash command so not creating the PR ultimately. I wonder if it's a model thing, or an opencode thing.

punkpeye•about 1 hour ago

Incredible model quality to price ratio

ls612•about 3 hours ago

How long does it usually take for folks to make smaller distills of these models? I really want to see how this will do when brought down to a size that will run on a Macbook.

simonw•about 3 hours ago

Unsloth often turn them around within a few hours, they might have gone to bed already though!

Keep an eye on https://huggingface.co/unsloth/models

Update ten minutes later: https://huggingface.co/unsloth/DeepSeek-V4-Pro just appeared but doesn't have files in yet, so they are clearly awake and pushing updates.

mohsen1•about 1 hour ago

"2 minutes ago" https://huggingface.co/unsloth/DeepSeek-V4-Pro

EnPissant•about 1 hour ago

Those are quants, not distills.

inventor7777•about 3 hours ago

Weren't there some frameworks recently released to allow Macs to stream weights from fast SSDs and thus fit way more parameters than what would normally fit in RAM?

I have never tried one yet but I am considering trying that for a medium sized model.

simonw•about 2 hours ago

I've been calling that the "streaming experts" trick, the key idea is to take advantage of Mixture of Expert models where only a subset of the weights are used for each round of calculations, then load those weights from SSD into RAM for each round.

As I understand it if DeepSeek v4 Pro is a 1.6T, 49B active that means you'd need just 49B in memory, so ~100GB at 16 bit or ~50GB at 8bit quantized.

v4 Flash is 284B, 13B active so might even fit in <32GB.

zozbot234•about 1 hour ago

The "active" count is not very meaningful except as a broad measure of sparsity, since the experts in MoE models are chosen per layer. Once you're streaming experts from disk, there's nothing that inherently requires having 49B parameters in memory at once. Of course, the less caching memory does, the higher the performance overhead of fetching from disk.

inventor7777•about 2 hours ago

Ahh, that actually makes more sense now. (As you can tell, I just skimmed through the READMEs and starred "for later".)

My Mac can fit almost 70B (Q3_K_M) in memory at once, so I really need to try this out soon at maybe Q5-ish.

zargon•about 2 hours ago

> ~100GB at 16 bit or ~50GB at 8bit quantized.

V4 is natively mixed FP4 and FP8, so significantly less than that. 50 GB max unquantized.

EnPissant•about 1 hour ago

Streaming weights from RAM to GPU for prefill makes sense due to batching and pcie5 x16 is fast enough to make it worthwhile.

Streaming weights from RAM to GPU for decode makes no sense at all because batching requires multiple parallel streams.

Streaming weights from SSD _never_ makes sense because the delta between SSD and RAM is too large. There is no situation where you would not be able to fit a model in RAM and also have useful speeds from SSD.

zozbot234•about 1 hour ago

These are more like experiments than a polished release as of yet. And the reduction in throughput is high compared to having the weights in RAM at all times, since you're bottlenecked by the SSD which even at its fastest is much slower than RAM.

the_sleaze_•about 3 hours ago

Do you have the links for those? Very interested

inventor7777•about 3 hours ago

Sure!

Note: these were just two that I starred when I saw them posted here. I have not looked seriously at it at the moment,

https://github.com/danveloper/flash-moe

https://github.com/t8/hypura

frozenseven•about 3 hours ago

Better link:

https://news.ycombinator.com/item?id=47885014

https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro

hongbo_zhang•about 3 hours ago

congrats

dhruv3006•about 2 hours ago

Ah now !

slopinthebag•about 2 hours ago

OMG

OMG ITS HAPPENING

shafiemoji•about 3 hours ago

I hope the update is an improvement. Losing 3.2 would be a real loss, it's excellent.

raincole•about 3 hours ago

History doesn't always repeat itself.

But if it does, then in the following week we'll see DeepSeek4 floods every AI-related online space. Thousands of posts swearing how it's better than the latest models OpenAI/Anthropic/Google have but only costs pennies.

Then a few weeks later it'll be forgotten by most.

sbysb•about 3 hours ago

It's difficult because even if the underlying model is very good, not having a pre-built harness like Claude Code makes it very un-sticky for most devs. Even at equal quality, the friction (or at least perceived friction) is higher than the mainstream models.

raincole•about 3 hours ago

OpenCode? Pi?

If one finds it difficult to set up OpenCode to use whatever providers they want, I won't call them 'dev'.

The only real friction (if the model is actually as good as SOTA) is to convince your employer to pay for it. But again if it really provides the same value at a fraction of the cost, it'll eventually cease to be an issue.

throwa356262•about 1 hour ago

    "If one finds it difficult to set up OpenCode to use whatever providers they want, I won't call them 'dev'."

I feel the same way. But look at the ollama vs llama.cpp post from HN few days back and you will see most of the enthusiasts in this space are very non technical people.

cmrdporcupine•about 3 hours ago

They have instructions right on their page on how to use claude code with it.