Live data from Hacker News

Show HN: Run an 80B Qwen in 4.3 GB of RAM on a Mac, and a 35B on an iPhone

github.com

61–70 of 149 posts

Re: Show HN: Run an 80B Qwen in 4.3 GB of RAM on a Mac, and a 35B on an iPhone

#61
post #29

Earlier quoted context omitted.

Most people are already used to rely on the internet on basically everything. At best, they download a tiny chunk of entertainment from it when they go on a plane, and as soon as they land they immediately abandon that offline chunk. In addition, LLMs, small or large, are highly parallelizable. This means that running on the same machine/GPUs many requests in parallel is significantly more efficient, and the sum of t…

I suspect the economics favor centralized servers, if you only look at the aggregated cost to serve X number of users' tokens. But we could say the same thing about a lot of the computation that iPhones do locally. They could have been much thinner clients, but instead they now have more compute power than desktops had when iPhones launched.

> I suspect the economics favor centralized servers, if you only look at the aggregated cost to serve X number of users' tokens.

The economics of real-time, low-latency inference of very large near-SOTA models will heavily favor a centralized setup. But if you can afford to wait for your answer - be it a day, a week, or even more at the extreme low end (or if you just stick to leaner models for your relatively quick replies) the economics start to shift in a very clear way. A slow-going local inference setup relying on cheap SSD offload does not need the high power input of a datacenter rack, and the cooling load is outright trivial - even when working on many requests in parallel, which (in a SSD offload context) is what maximizes throughput even for local inference. These are serious problems for centralized inference that will probably limit the scale at which it can be applied.

Re: Show HN: Run an 80B Qwen in 4.3 GB of RAM on a Mac, and a 35B on an iPhone

#62
post #49

I know everyone wants to crap all over these setups that are impractical, but this is how progress happens. People will keep plugging away at this and figure out how to avoid wearing the hard drive, how to make it run faster, custom hardware buses etc. Keep going! I personally can't wait for the day when a 1t param model runs off a $200 SSD instead of a $50k rack of Nvidia chips.

Seems like what Apple's going for with afm3. Their latest model that will be embedded in macOS 27 is a quantized dense 20B that only select between 1 to 4B at inference, based on the prompt, not token by token. If only they could make a 100B or 400B dense that selects ~5 to 15B...

I don't understand, if they are only using a subset of the tokens then it's a sparse model. What do you mean by dense?

Re: Show HN: Run an 80B Qwen in 4.3 GB of RAM on a Mac, and a 35B on an iPhone

#63
post #50

Earlier quoted context omitted.

(1) Yes. (2) Are you saying that you think we're at the limits of computing in general, or that specific technology? We know, for example, that a human brain level intelligence is possible to run on a human brain. We are nowhere near that. And actually that's not even a physical limit necessarily. But that is...not a low hanging fruit.

> We are nowhere near that. Nowhere?

Leaving aside the discussion on LLMs intelligence vs human intelligence, on a purely energy consumption level we are definitely and without any possible questioning nowhere near that indeed.

Re: Show HN: Run an 80B Qwen in 4.3 GB of RAM on a Mac, and a 35B on an iPhone

#64
post #62
post #49

Earlier quoted context omitted.

Seems like what Apple's going for with afm3. Their latest model that will be embedded in macOS 27 is a quantized dense 20B that only select between 1 to 4B at inference, based on the prompt, not token by token. If only they could make a 100B or 400B dense that selects ~5 to 15B...

I don't understand, if they are only using a subset of the tokens then it's a sparse model. What do you mean by dense?

Could it be some sort of permanently routed MoE where they detect and switch for the whole prompt instead of token by token?

Re: Show HN: Run an 80B Qwen in 4.3 GB of RAM on a Mac, and a 35B on an iPhone

#65
post #20
post #10

Earlier quoted context omitted.

Haha 1T on $50k might be a bit hopeful, mate, even at FP8. But I too am hopeful.

8800 GTX in 2006. Cutting-edge, an insanely powered consumer card for the time. Theoretically around 0.3456 TFLOPS. 1080 GTX in 2016. Cutting-edge, an insanely powerful consumer card for the time. Theoretically around 8.87 to 8.9 TFLOPS. 5090 RTX in 2026. Cutting-edge, an insanely powerful consumer card for today. Theoretically around 104.8 TFLOPS. In the same timeframe mobile processor CPU's went from 0.001 TFLOPS,…

Speaking of ASICs - how likely is it that as models get better we'll see someone baking a whole model directly into the silicon? It's like having l0 cache.

Re: Show HN: Run an 80B Qwen in 4.3 GB of RAM on a Mac, and a 35B on an iPhone

#66

Earlier quoted context omitted.

What hardware advances would we need to see for that to happen? It feels like everything in that arena has kind of plateaued.

I could definitely image Apple embedding a kind of LLM-optimized FPGA: slow to load (update) an LLM, but blazing fast at computing tokens. Who needs memory when your model is set in silicon ?

You don't an FPGA if you're taping out your own chips. But that is just a MMA accelerator with decent memory bandwidth. No secret sauce here.

Re: Show HN: Run an 80B Qwen in 4.3 GB of RAM on a Mac, and a 35B on an iPhone

#68
post #20

Earlier quoted context omitted.

8800 GTX in 2006. Cutting-edge, an insanely powered consumer card for the time. Theoretically around 0.3456 TFLOPS. 1080 GTX in 2016. Cutting-edge, an insanely powerful consumer card for the time. Theoretically around 8.87 to 8.9 TFLOPS. 5090 RTX in 2026. Cutting-edge, an insanely powerful consumer card for today. Theoretically around 104.8 TFLOPS. In the same timeframe mobile processor CPU's went from 0.001 TFLOPS,…

Speaking of ASICs - how likely is it that as models get better we'll see someone baking a whole model directly into the silicon? It's like having l0 cache.

You could do it but there would be no point, The only advantage over would be power consumption. And it would be quite expensive.

At the rate models are improving, it would be obsolete in six months.

Re: Show HN: Run an 80B Qwen in 4.3 GB of RAM on a Mac, and a 35B on an iPhone

#69
post #3

At what, 10 tokens per hour? These disk swapping methods all have the same drawbacks - kill your drive early, and slow as hell.

Am I the only one that has no flash lifetime anxiety? I still have drives from more than a decade ago that keep on chugging fine.

I remember the time spinning rust was the only option and reliable they weren't. In 30 years of computing I have had more than ten hdds and zero ssds die.

Re: Show HN: Run an 80B Qwen in 4.3 GB of RAM on a Mac, and a 35B on an iPhone

#70

Earlier quoted context omitted.

Speaking of ASICs - how likely is it that as models get better we'll see someone baking a whole model directly into the silicon? It's like having l0 cache.

You could do it but there would be no point, The only advantage over would be power consumption. And it would be quite expensive. At the rate models are improving, it would be obsolete in six months.

Power consumption and latency are very important on mobile
Post reply on HN