Re:Show HN: Llama 3.1 70B on a single RTX 3090 via NVMe-to-G...
by fluoridation on Saturday February 21, 2026 @10:56PM
(#47107992)
That's slower than just running it off CPU+GPU. I can easily hit 1.5 tokens/s on a 7950X+3090 and a 20480-token context.
[ Parent
| on HN ]
There are no comments on this comment yet.