login sign up

Llama 3.1 70B on a single RTX 3090 via NVMe-to-GPU bypassing the CPU

github.com · first added by @hn_wayback
saved by
1 person
discussions · 1
Show HN: Llama 3.1 70B on a single RTX 3090 via NVMe-to-GPU bypassing the CPU 394 pts · 101 comments · Feb 2026 394 pts · 101 comments · Feb 2026
0 people saved or upvoted this