[HN Gopher] Show HN: Llama 3.1 70B on a single RTX 3090 via NVMe...
___________________________________________________________________
Show HN: Llama 3.1 70B on a single RTX 3090 via NVMe-to-GPU
bypassing the CPU
Hi everyone, I'm kinda involved in some retrogaming and with some
experiments I ran into the following question: "It would be
possible to run transformer models bypassing the cpu/ram,
connecting the gpu to the nvme?" This is the result of that
question itself and some weekend vibecoding (it has the linked
library repository in the readme as well), it seems to work, even
on consumer gpus, it should work better on professional ones tho
Author : xaskasdf
Score : 8 points
Date : 2026-02-21 20:57 UTC (2 hours ago)
(HTM) web link (github.com)
(TXT) w3m dump (github.com)
| randomtoast wrote:
| 0.2 tok/s is fine for experimentation, but it is not interactive
| in any meaningful sense. For many use cases, a well-quantized 8B
| or 13B that stays resident will simply deliver a better latency-
| quality tradeoff
___________________________________________________________________
(page generated 2026-02-21 23:00 UTC)