Baseten runs DeepSeek v4.1 Flash at ~2500 tok/s on Vera Rubin
Baseten reported that DeepSeek v4.1 Flash achieves about 2500 tokens per second on Nvidia's Vera Rubin hardware using batch size 1 and TP4 configuration, showcasing its latest low-latency inference optimizations.
2026-11-17 ~ 2026-11-17 · 2 related posts
- Episode 1: Baseten Open-Sources Rust+CUDA DeepSeek Inference Engine Built From Scratch(2026-11-14, 2 posts)
- Episode 2: Baseten runs DeepSeek v4.1 Flash at ~2500 tok/s on Vera Rubin(2026-11-17, 2 posts)
- DeepSeek v4.1 Flash hits ~2,500 tok/s on Vera Rubin in Baseten low-latency tests — baseten · 2026-11-17
- Baseten hits ~2,500 tok/s on DeepSeek v4.1 Flash with Vera Rubin, 1.7x faster than GB300 — baseten · 2026-11-17