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
- Episode 1: DeepSeek-V4-Flash Benchmarks Show Up to 4,550 tok/s on a Single GB300(2026-08-19, 2 posts)
- Episode 2: Stanford's Open Framework Helps DeepSeek V4 Flash Outperform Claude(2026-08-20, 2 posts)
- Episode 3: DeepSeek Flash Usage Surges as Ultra-Cheap Inference Draws Enterprises(2026-08-21, 3 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