MiniMax M3.1 Flash TP4 on 4x DGX Spark: 39.7 tok/s prose decode, 262k context
First measured bring-up of M3.1 Flash with TP4 across four DGX Sparks: 39.7 tok/s prose and 62.2 tok/s structured decode at c1, 166/261 tok/s aggregate at c16, 262k context with ~1.37M-token FP8 KV cache, using MiniMax's NVFP4 experts and MXFP8 weights, with a full recipe posted.
MiniMax-M3.1-Flash TP4 on 4× DGX Spark, day 0 🐇 • Prose decode: 39.7 tok/s at c1 • Structured decode: 62.2 tok/s at c1 • Aggregate: 166 tok/s prose, 261 tok/s structured at c16 • speedbench quick: 38.4 tok/s across 30 prompts • 262k context, ~1.37M-token FP8 KV cache • MiniMax's own NVFP4 experts + MXFP8 weights, bundled DSpark draft • Runs on GB10 (sm_121): FP8 KV, Triton sparse attention, Marlin experts (the NVFP4 KV cache is SM100-only) First measured bring-up. Speed tuning and quality gates are next. Full recipe, measurements and credits: https://github.com/knapcio/MiniMax-M3.1-Flash-4x-DGX-Spark-TP4