Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac

github.com

Post reply on HN
Print view View original

251–260 of 382 posts

Re: Show HN: Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac

#251

Post by oezi »

giancarlostoro wrote: post #92

Nice, I think this is the second time I see this here on HN, I always wondered why we need to shove the entire model into memory, I don't care who King Charles is every single time. It always felt as though we already figured out how to break up large files and parse them efficiently with very little memory. Frontier AI feels like its full of people who are brilliant at making models, but when it comes to scale and p…

One key thing with MoE I am still not understanding is why we don't keep the same expert in memory for a larger number of tokens than 1. Why do we route to some other expert every token? Wouldn't it be more memory efficient to generate at least 2,3,4,8,12 or 32 tokens and then swap the experts?

Re: Show HN: Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac

#252

Post by zozbot234 »

oezi wrote: post #251
giancarlostoro wrote: post #92

Nice, I think this is the second time I see this here on HN, I always wondered why we need to shove the entire model into memory, I don't care who King Charles is every single time. It always felt as though we already figured out how to break up large files and parse them efficiently with very little memory. Frontier AI feels like its full of people who are brilliant at making models, but when it comes to scale and p…

One key thing with MoE I am still not understanding is why we don't keep the same expert in memory for a larger number of tokens than 1. Why do we route to some other expert every token? Wouldn't it be more memory efficient to generate at least 2,3,4,8,12 or 32 tokens and then swap the experts?

Expert choice actually happens per layer, not just per token. It's not a limitation when doing inference at scale since all experts are then loaded in fast VRAM anyway. It's mostly just a way to enforce some kind of model sparsity and save on compute.

The new version of Apple Foundation Model (AFM) Core Advanced is an exception, it actually routes experts per prompt (with sporadic rerouting perhaps?) which is more in line with what you're proposing. But this will theoretically make the model less smart than a similar one where experts are picked per layer.

Re: Show HN: Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac

#253

Post by nosyke »

IdontKnowRust wrote: post #196
Keyframe wrote: post #168

Earlier quoted context omitted.

I don't care who King Charles is every single time that's the trick and a multi-billion dollar question, how would an llm engine know that? it's an active research area how to cull the initial layer surface and do the optimal traversal path through the layers and it's a damn hard problem. It's definitely an area where a ton of performance is left on the table still.

This makes me think (by full ignorance) how quantum computing can be useful in this field of things reach a stable-ish point

it's just not something you would ever use a quantum computer for

Re: Show HN: Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac

#254

Post by hacket04 »

tpurves wrote: post #55

Okay this tidbit is interesting to me "5–6 tok/s M2 -> 31–35 tok/s on an M5 Pro". So where will be in just another gen or two? my impression right now is that M5 gen is on the cusp of practicality for local inference. If techniques like OPs here, start to make the RAM situation more amenable, by the time we get to M6 or M7 (or AMD's equiv next gen APUs on TSMC N2 nodes), local AI could be ready to go much more mainst…

I think it's M5 MacBook Pro, not M5 Pro, as he mentioned.

Re: Show HN: Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac

#255

Post by glitchc »

giancarlostoro wrote: post #92

Nice, I think this is the second time I see this here on HN, I always wondered why we need to shove the entire model into memory, I don't care who King Charles is every single time. It always felt as though we already figured out how to break up large files and parse them efficiently with very little memory. Frontier AI feels like its full of people who are brilliant at making models, but when it comes to scale and p…

Indeed, it begs the question why we have "everything" models where instead we could have very efficient "something" models. Typical LLMs out there can generate code and translate between 60 different languages. Sometimes I only need the first part, sometimes the second. Two distinct models would be a lot smaller and run much faster (token-wise).

Re: Show HN: Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac

#260

Post by quasarj »

xenonite wrote: post #48

With my M1 MBA, I am still on macOS 15. To compile it, just remove the two lines with opts.languageVersion = .version4_0 or surround them with if #available(macOS 26.0, *) { opts.languageVersion = .version4_0 } You'll miss out on a prefill speedup of 2.4x (as it yields 11.24x faster attention), according to the git comments, but it works. (On the 8-GPU-core MBA M1, I get 5-6 tok/s.)

Why are you still on 15?
Post reply on HN