Full-precision DeepSeek 4.1 Flash hits 300+ TPS on 4 RTX Pros with custom vLLM fork

TheZachMueller · x · 2026-09-11

A developer (@fraserpricee) demonstrated running full-precision DeepSeek 4.1 Flash at 300+ TPS on four RTX Pro cards, with under 32GB peak system RAM, using a custom vLLM fork and a small SSD. The full recipe is promised to be published later; for now it's a teaser of the local inference setup.

Original post →

More from Infra

Infra channel →