Minimax-M3-NVFP-3x-DGX-Sparks-TP-3. Working recipe: MiniMax-M3 NVFP4 at tensor-parallel 3 across 3x DGX Spark (GB10/sm_121) with clean tool-calling. Includes the head-node OOM fixes and multi-node Ray/NCCL setup. Open for tinkering + fixes.

github.com/tonyd2wild/Minimax-M3-NVFP-3x-DGX-Sparks-TP-3

Vaya's read on this project

Problem, audience, market, and the verdict — sign in to see it.

Updates

No recent activity.