DeepSeek-V4-Flash Benchmarks Show Up to 4,550 tok/s on a Single GB300

Benchmarks show DeepSeek-V4-Flash reaching 286 tok/s single-stream and 4,550 tok/s at 32 concurrency on a DGX Station GB300, with speculative decoding adding a 34% speedup.

2026-08-19 ~ 2026-08-19 · 2 related posts

• DeepSeek-V4-Flash benchmarks: 286 tok/s single-stream, +34% boost with speculative decoding — mcraddock · 2026-08-19
• DS4F benchmarks hit 261 t/s single-session, 1479 t/s batch-16 on GB300 DGX — antirez · 2026-08-19