A custom fork for frontier-scale mixture-of-experts inference on an RTX 3060 with 12 GB VRAM, 16 GB system RAM and local NVMe

programming.dev· rss · 0 points · Oct 31, 2026

programming.dev

A custom fork for frontier-scale mixture-of-experts inference on an RTX 3060 with 12 GB VRAM, 16 GB system RAM and local NVMe

0 comments

Sign in to join the discussion — your thebay.events account works here.

No comments yet.