I know relatively little about the workings of LLMs, but I keep seeing projects like this that run massive MoE models using very modest amounts of RAM, perhaps excessively so. I wonder, is there a way to make the RAM usage tunable? I have a Macbook with 32 GB of RAM, and it'd be great if I could run the same model but take advantage of the additional RAM to make it run faster.
That's about the turning point for just using typical quants for me. Larger still and you can just do the full model. Smaller to this degree and you need all sorts of extra tricks to get anything.
I read a comment on here a few months back I wanna restate. Basically, there is a good chance that Apple is betting that the LLMs in the future will be so efficient that those that consumers will use everyday will be easily computed by the iPhone or even bigger ones on Macs. Honestly makes the most sense that we are heading that way in a few years latest.
The models themselves have far from plateaued. Maybe someone finds a way to get a really capable model down to, say, 12GB of ram. Then we'd be in business.
this is cool but like, are we just vibe coding NAND burners at this point? these decode times don't really tell the whole story, because prefill becomes the bottleneck.
half an hour to process 10k tokens on an M5 seems... not great
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.
Haha 1T on $50k might be a bit hopeful, mate, even at FP8. But I too am hopeful.
AMD already demonstrated 1T on strix halo clusters. << $10K at original MSRP.
I know relatively little about the workings of LLMs, but I keep seeing projects like this that run massive MoE models using very modest amounts of RAM, perhaps excessively so. I wonder, is there a way to make the RAM usage tunable? I have a Macbook with 32 GB of RAM, and it'd be great if I could run the same model but take advantage of the additional RAM to make it run faster.
That's about the turning point for just using typical quants for me. Larger still and you can just do the full model. Smaller to this degree and you need all sorts of extra tricks to get anything.
I guess you have to know which experts to keep “hot” in ram, which you can’t know beforehand, so there wouldn’t be much gain.
I read a comment on here a few months back I wanna restate. Basically, there is a good chance that Apple is betting that the LLMs in the future will be so efficient that those that consumers will use everyday will be easily computed by the iPhone or even bigger ones on Macs. Honestly makes the most sense that we are heading that way in a few years latest.
What hardware advances would we need to see for that to happen? It feels like everything in that arena has kind of plateaued.
The models themselves have far from plateaued. Maybe someone finds a way to get a really capable model down to, say, 12GB of ram. Then we'd be in business.
It could be on software side too. OpenAI has certainly not plateaued.
At what, 10 tokens per hour? These disk swapping methods all have the same drawbacks - kill your drive early, and slow as hell.
It says very prominently in the post: 4.5-5t/s for 80b on an M5
Isn’t it only writes that kill drives?
Yeah, that's why most of these comments seem weird to me.
Yes for NAND, and I suppose nobody is using mechanical hard drives for this.
this is cool but like, are we just vibe coding NAND burners at this point? these decode times don't really tell the whole story, because prefill becomes the bottleneck.
half an hour to process 10k tokens on an M5 seems... not great
Not great for coding, or realtime agent interactions. But for background processing tasks overnight? Seems like it’d work pretty well