GLM-5.3 is now open-weight

It is absolutely not worth buying hardware to run models for purely (long term) cost reasons. For open weights models the economies of scale means the cloud beats local significantly and your payback time is like 10 years.

However there are other reasons (e.g. privacy) that might make it worth running locally for some people.

So far I don’t regret buying an M1 Max device with 32Gb of RAM. The models available for it keep getting better (running just about okay for interactive use) and 400 GB/s of bandwidth is still considered a lot.

The models are currently improving much faster than the hardware and this doesn’t seem to have plateaued yet.

My colocation costs come up at £7k a year for 3u. 1xu in prime dc, 2x1u in another DC for backup

My rented H200 server comes at just over £120 a day, £3.2k~ a month. Minimum two year contract.

I don't want to, but I am having to say bye to my 2x1u.

That's basically the question I'm trying to answer.

If you're paying Anthropic or OpenAI to use their models, harness, governance, etc., I could see the local inference potentially coming out ahead. They're already starting to ratchet down what your money gets you on their platforms, and that can be expected to continue as the leaders of those companies continue to seek the road to the El Dorado that is being a trillionaire.*

If you're looking to get into the guts of AI development instead of having it handed to you by a provider, that's where it gets murky. I'm wanting to write some sort of agent that does things and get into making outputs consistent in the like, and I'm not sure whether to host something on GCP or buy an M5 Mac.

*Note: El Dorado is a mythical city and many people died trying to find it.

> "dual xeon"

Does inference make full use of the memory bandwidth in a NUMA system?

You'd also likely spend far more in electricity than the API cost of processing the prompt(s)

I have a dual epyc + 1TB RAM. I could push glm 5.2 to 7 tok/s CPU only.

I’ll be very curious what you get with DDR4. I also almost went that way. I have an Epyc DDR 5 rig and the best I see is 10 tok/s. Caveat being that’s at Q8 and a 4090 doing pre fill so it could be pushed up.

The surprising thing for me is how much work you will need to cool the banks if you’re near your memory ceiling. My memory starts soft throttling at about 74C (dies may be hotter, that’s the bank temp) and will turn down speed to try to stay below 80.

Happy to send my llama.cpp config settings if you want it.

Curious about that price, if you don't mind sharing a ballpark

Depending on which Epyc you got it might be slower than 1/5 of the speed.

Honestly I suspect neither of them will be performing terribly well but with DDR4 3200 RAM I wonder if you'll be counting tokens per second or seconds per token. I mean, you do at least get a lot of memory channels at least, compared to consumer PCs. I am curious to hear what performance you get, I feel there is not enough information out there on what different setups manage to eek out.

Not every tech worker is making top-tier US salaries. For some (I suspect not few) people on HN that $20,000 Mac is almost a year's salary.

You are allowed to have an opinion on her 20k bag addiction

> If you wanted to ask a 2002 person what they thought about future historical events you can just ask them directly.

The weights arent the truth tho, maybe a timecapsule-vhs but i wouldnt trust llm weights more than more hardcore deterministic media that might get preserved to infer facts from an era.

The companies doing the training are becoming the "winners" that are "rewriting history" as they train their models.

Maybe I'm reading too much between the lines, but I suspect the reason is to rub his nose in the duplicity or naivety depending on how generous you're feeling. Publishing the model would be a confession that he was wrong.

AI policy is being shaped somewhat by the things Sam and Dario say. So even if you're not feeling vindictive, it's probably good to keep a track record of the previous things they have said as a Bayesian prior. People who don't know better listen to these people, and maybe they shouldn't.

GPT-3 is a different model than gpt-oss and is therefore not an answer to the question.

I cannot stand using gpt-oss, but I miss some of the creative spark of GPT-3 davinci dearly.

At release, GPT-OSS was arguably a few generations behind the open frontier.

NVFP4 ~20-30tps (MTP + vision, no dflash2).

I hear the argument here, but isn't it possible it has dramatically more knowledge and when you get outside the common cases many of us use it for, it'll have completely different capabilities?

I feel like most benchmarks cluster on a reasonably limited area of human knowledge

It seems like there is tradeoff between model size and the need for tool use, which - in my mind - is quite costly in terms of time and tokens. More detailed world knowledge requires an exponential increase in model size, but most knowledge can be acquired ad hoc using search or database queries. This will fail for questions where the model lacks the knowledge to ask the right questions, but maybe this could be solved by a handful small inquiry models with different knowledge encoded in their weights?

You can't compare models released 6+ months apart. GLM 5.2 was same architecture as 5.3 and not nearly as good. Takes time to build frontier intelligence and distill down to smaller sizes.

> that would prove rather embarrassing for Anthropic

Not really, in that you just work with different constraints.

Anthropic and US labs in general has maybe 100s to 1000s of GPUs per person to experiment. Zai and Chinese labs in general have 1-10.

The priorities are different.

My second favorite model by now is GLM 5.3 flash which is very capable of day to day task. I use it as the main model and GLM 5.3 for task that is more complex

z.ai coder plan, both in opencode and direct API access. I use it for my side projects like https://github.com/scosman/Biscotti (on-device meeting transcription and summaries).

I have seen you advertise your website a few times. I like the idea of not having to trust the router, so I took some time out of my day to critique your website: https://files.catbox.moe/v68cf7.png

My visit to your website went like this:

1. Visit models page

2. Try to find GLM-5.3-Flash (which is among the ~5 models that 90% of people currently care about)

3. Give up scrolling (which would have taken OVER 50 SCROLLS!!!) and use Ctrl + F

4. Try to find input/output/cached price

5. Scroll all the way up to find out which column is what

6. Notice that output price is cut off

7. Notice that the scroll bar is over 100 scrolls further down the page

8. Use Shift + Wheel to scroll horizontally (most visitors probably won't know this trick)

9. Notice that cached price is missing

10. Conclude that this is probably not a serious offering and bounce

There are probably more issues later on, but this is how far I got.

I would suggest you to:

- Deslopify all pages that a user may visit before conversion

- List important models first (see OpenRouter rankings)

- Move the most important information (model name/input/output/cached price) to the left

- Measure cache hit rate and compute effective price PER PROVIDER (see OpenRouter)

(- Optional: Fix the broken link on your HN profile page)

It's interesting that OpenCode Go is treating it as 2x more expensive than DeepSeek Flash, even factoring in the 50% discount

z.ai is using all Chinese hardware for flash: https://thenewstack.io/glm-5-3-flash-chinese-chips/

There are other providers with much faster inference, like BaseTen at >100t/s: https://openrouter.ai/z-ai/glm-5.3-flash#performance

I think we don't have a good draft model for better speculative decoding yet (e.g. DFlash 2). Once we do, it will be faster.

Yeah I used Ox alpha earlier this week when it was free and deepseek flash when it was free on opencode. Both were great. Z.ai’s subscription doesn’t look very good versus the others.

I burn through my current Google AI pro sub for the week in about 2 and a half days so wanted something extra to add to it, but don’t want to buy any expensive ultra plan. Flash models have got me about 98% of what I need, but quotas are still a bit low.