ES version is available. Content is displayed in original English for accuracy.
Advertisement
Advertisement
⚡ Community Insights
Discussion Sentiment
90% Positive
Analyzed from 2523 words in the discussion.
Trending Topics
#models#local#model#run#running#using#setup#performance#qwen#ram
Discussion (72 Comments)Read Original on HackerNews
GLM-5.3-Flash at true 8-bit: 341 GB on disk, 328 GB resident, 288 experts across 46 layers, loads in 65 seconds. • 18.7 tokens/s generation, 35 tokens/s prompt, on a desk, on a $0 per-token bill. • Runs beside our whole agent city on one box with ~130 GB to spare. • Review test: caught 6 of 6 planted P1 defects, zero false positives, same score as the frontier model we pay for. • CRM test: 11 of 11 required records extracted, zero wrong writes, 45 minutes, first local model to clear the bar. • Serving a 131k-token window today; the model itself supports 1,048,576. Widened to 4 concurrent slots and still have 50gb+ of excess ram.
granted my cto still isn't moving all of our inference to glm5.3 but we've identified 40%+ that is currently handled by fable that we're routing locally instead and will do concurrent requests to verify/compare responses for a while.
On a Laptop with 32 GB RAM and Iris Xe integrated graphic card, I get between 11-18 Tokens/Second with Qwen 3.8 27B and llama.cpp with sysl Intel optimisations. Same results with the vulkan back end, although sometimes it ends in weird segmentation faults due to the memory consumption.
Which are...?
1. Getting information (such as information about hardware unfamiliar to me) when not connected to the internet, which happens occasionally in my case.
2. Continuing to learn Rust by way of toy examples, puzzles, and comparing aspects of various solutions, for example from LeetCode.
3. Reformatting data, for example from a PDF to a markdown table, or converting receipt images to text.
4. Simple translation/explanation (e.g. I'm teaching my wife one of the languages I speak but sometimes may not know/have the words to explain the full nuance of a translated word).
5. Summarization. One of the webnovels I'm reading has some very boring parts I don't want to slog through, in those cases I simply make the LLM summarize that part and move on.
Etc., you get the idea. It's not unusable for coding, but it would make many mistakes when making a whole feature and the context lengths are limited to around 30k-40k tokens by my RAM. I could give it access to the web but I simply use an online model when I need that sort of thing, again partly due to the context limit.
Edit: The MLX version of Gemma 4 26b a4b does about 62 tok/s.
If you are work from home and do dishes between prompts you can get a gpt3-like result.
I found it useful when I was... Well I didn't find it useful. But an Nvidia 3060 let me ask unethical questions pretty fast.
With an 8x MI355x cluster at full tilt and including cooling, your power draw runs ~17kW. That's what it looks like when it's running full tilt. To be fair, hey that's pretty expensive. It does mean 8 multi-trillion parameter models unquantized running 24/7 without pause. And you get the full month like that, your monthly token limit is the time in a month. That cluster, the electrical upgrade, the cooling setup, and the electricity to run it all costs less in 2 months than your maximum affordance from Anthropic does in the same time period. Two billing cycles, and realistically it's more like two weeks. In 4 quarters you've wasted over a million. Like, what are we talking about here?
Now if you aren't using AI all that much, which is perfectly valid, and especially if you aren't using it at its absolute maximum, the story changes. Because even though at that point you're not paying nearly as much in electricity to run the cluster anymore, you still have the $300k+ capex to get the setup in the first place. But if we're not redlining it non-stop, then we're not really talking about performance anymore, are we? If your org never comes close to hitting token limits, it's probably because AI is rather marginal for you. Which again, is perfectly valid. I don't even use AI professionally.
Fact of the matter is, if your corp can justify the capex for a cluster and makes heavy use of AI, you are literally burning money by not having one in your building. The numbers are painfully obvious. Even deepseek isn't as cheap. This is before we get into things like LoRAs, custom inference pipelines, etc. which you know are kind of important if you actually care about model performance.
Pretty expensive is an understatement. You couldn’t buy one of these if you wanted to right now. If you could it would be multiple hundreds of thousands of dollars.
> It does mean 8 multi-trillion parameter models unquantized running 24/7 without pause
You can’t even run one unquantized multi-trillion parameter (>=2T) model on 8 x MI355x with enough context for concurrent users. I don’t know how you think it’s going to run 8 of them at the same time. Did you mean 8 concurrent sessions?
Your math is way off across this post. If replacing an Anthropic subscription for a whole company was as easy as buying a box for the office and then breaking even in 2 months, it wouldn’t be some little secret that we only discover in a comment online.
99% of the cost was in input tokens, I only used like 100k ish output tokens. It was a one shot task asking the agent to implement proxy injection to Guice. It did a pretty amazing job.
If you were to use hosted LLMs for a lot of agentic coding, a maxed out M5 Ultra Mac Studio would pay for itself in under a year.
He was a lead engineer, so after he announced it wasn't going to work, everyone pretended it never happened. But we all knew.
That said, it is really cool to be able to run an LLM on eg a Mac laptop. Just not a better experience on almost any metric for interactive use than eg Claude Code, beside privacy and guardrails.
How's the actual performance of Qwen 3.8 27B? On deepswe it supposedly performs slightly worse than gpt 5.6 luna high[1], but I can't help but think they've been benchmaxxed.
[1] https://deepswe.datacurve.ai/, https://unsloth.ai/docs/models/qwen3.8#benchmarks
A friend and I were actually discussing today how benches show Luna Max at about par on coding with Sol Medium, but how it's nowhere near in reality. We were speculating that maybe it's because a lot of benches are best-of-n, and should probably be worst-of-n, because variance in performance is killer with large coding projects. Consistency is what lets you actually build on this stuff.
https://quesma.com/benchmarks/babaisbench/
---
Qwen3.8-27B-4bit, Prompt Processing (PP) 66.3 tok/s, Token Generation (TG) 11.8 tok/s
Ornith-1.5-35B-A3B-MLX-4bit, PP 379.7, TG 45.8
Ornith-1.5-35B-A3B-MLX-4bit, PP 381.5, TG 46.4
Qwen3.6-35B-A3B-mxfp4, PP 389.6, TG 47.6
Qwen3.6-35B-A3B-OptiQ-4bit, PP 342.6, TG 44.4
---
Qwen3.8-27B-4bit generally runs out of output token before completing the task though excellent partial results.
Ornith-1.5-35B-A3B-MLX-4bit seems to get in the loop often specially with tool calls.
Qwen3.6-35B-A3B-mxfp4 seems to be optimal with speed and quality output.
I am going to test Qwen3.6-35B-A3B-4bit soon with same code block just to check my intuition that any derivatives don't seem to perform better than the originals.
This is the burning question for me, what are they doing with our hard work.
I'd have thought that sherlocking a user's $10M business would be too high risk, given the billions at stake if real evidence of this happening was found.
However, OpenAI are currently being sued by Apple for trade secret theft, and the way it was done seems to be abundantly idiotic.
So I'm torn.
If there was a "Mullvad of GPU clouds", would that solve the privacy concerns?
These are really good models but the harness has to be built around them. I have a ton of generated system prompts for specific purposes. Even parts of a SolidJS stack, for example Route management, has its own prompt. These are experiments but the results are real. If we build harnesses around small models, we can build a locally running WYSIWYG editor which works on plain text prompts.
The performance, in simple tokens/second, is not the most important factor. For many private data points, like emails, I would rather have a local graph based search and LLM on top where the harness is specific to problems like calendar, contacts, finance, etc.
I run all experiments on an 16GB M4 Mac Mini but coding agents building the harness are a mix of Codex, Claude Code and opencode.
I've since acquired two DGX Sparks, and it feels so much snappier.
[0]https://github.com/antirez/ds4
the sparks have much slower memory bandwidth is the trade off
Another benefit of the 2x spark setup is that you can parallelize to ~6 streams pretty efficiently.
All depends on the workflows you’re using it for.
I’m quite excited for the M7 class machines.
Meanwhile the stock market has Nvidia at the top... Until everyone gets cuda.
https://x.com/mkagenius/status/2093730391429685732
(xcancel seems to have received a cease and desist)
Is that supposed to be hallucination? The human or other kind. Feels like a made up URL. It's .ai, isn't it?
Not many people share setup with actual setup handholding so that was very G of you
Agents require at least DeepSeek pro and even that is the minimum.
You might be able to get a good model to write instructions and run it in smaller models.
Otherwise, cool your AI got the current weather.
I wanna get a desktop Mac for local ai so that I don’t turn my laptop into a delta 15k rpm fan when I run things.
I guess I’ll get in line for one hah.
I am curious is what is the 80% request served by this setup, I was using it for OpenClaw which run serveral cron jobs that discover stuffs over the wide internet, check my support system's unanswered tickets, browser X and some social media for me to filter the valued ones(though I have to say even with GPT 5.6 sol, the quality is low for the timeline X sent to me)
Btw, Tailscale is quite cool and did a good job, I was using it to serve the local LLM and connct the openclaw on a Linux Machine to it.