deepseek-v4.1POST

DeepSeek V4.1 Flash on 4 DGX Sparks: 70 tok/s single stream

Running stock DeepSeek V4.1 Flash with SGLang on four DGX Sparks in a switchless ring gives 70.0 tok/s on single-stream code and 72.9 tok/s total across 4 streams (26.2 each).

Kevin Theo

@kevintheooArchived 4 days agoOriginally posted 2026.10.26

Kevin Theo @kevintheooOriginally posted 2026.10.26

Open original on X

@MiaAI_lab @ashxhart @volatilemarkts running your SGLang recipe on 4 Sparks in a switchless ring. stock DeepSeek V4.1 Flash here: 70.0 tok/s on code single stream, 72.9 total at 4 streams (26.2 each). 16 sessions at full 1M is a different league. will rerun my prompts on TensorFold when the recipe drops

x.com/kevintheoo/status/2114439034558623822Archived 2026.10.26 12:04