Re:MLC-LLM: GPT/Llama on consumer-class GPUs and phones
by valine on Sunday April 30, 2023 @06:07PM
(#35767028)
It’s useful because you can buy a Macbook with 64GB of RAM, and then use that RAM as VRAM to run your LLM.
[ Parent
| on HN ]
There are no comments on this comment yet.