minimax-m3.1POST
MiniMax M3.1 Flash weights on Hugging Face: fits 4 DGX Sparks at tp4
Local-deployment notes: 428B MoE with 23B active, 1M context, multimodal, ~250GB QAT checkpoint; Artificial Analysis score 42 ties GLM-5.3-Flash. Two DGX Sparks are too tight with context, four at tp4 fit comfortably, no Spark benchmarks yet.
𝙒𝙞𝙡𝙘𝙤 𝘷𝘢𝘯 𝘽𝙤𝙭𝙩𝙚𝙡 ⚡🚀🧲🌞
@nuonrgArchived 4 days agoOriginally posted 2026.10.23
𝙒𝙞𝙡𝙘𝙤 𝘷𝘢𝘯 𝘽𝙤𝙭𝙩𝙚𝙡 ⚡🚀🧲🌞 @nuonrgOriginally posted 2026.10.23
MiniMax-M3.1-Flash open weights are live on Hugging Face: 428B MoE with 23B active, 1M context, multimodal, ~250GB QAT checkpoint. Artificial Analysis has it at 42, on par with GLM-5.3-Flash. Too tight for 2 DGX Sparks once you add context, but it fits comfortably on 4 with tp4. No Spark benchmarks yet. https://huggingface.co/MiniMaxAI/MiniMax-M3.1-Flash
x.com/nuonrg/status/2113538680807625091Archived 2026.10.24 12:10