Baseten runs DeepSeek v4.1 Flash at ~2,500 tok/s on Vera Rubin, 1.7x faster than GB300

baseten · x · 2026-11-19

Baseten shared new low-latency inference results for DeepSeek v4.1 Flash on NVIDIA's Vera Rubin platform:

NVIDIA's AI Infra account publicly congratulated the teams, making this one of the earliest notable low-latency benchmarks on Vera Rubin.

Original post →

More from Infra

Infra channel →