Open Source MiniMax H3 Inference Engine for Mac

QuixiAI · x · 2026-08-25

QuixiAI has open-sourced the MiniMax H3 inference engine h3.c, tailored for Mac computers. Forked from antirez/h3.c, it adds GGUF support, multi-GPU capabilities, and a graphical user interface to enable efficient local execution of the H3 model.

Original post →

More from Infra

• 4070 Ti Benchmarks: Running Kimi K3, DeepSeek V4, and Qwen 122B Locally — JayB_Official · 2026-08-25
• CXMT LPDDR6 revealed, Xiaomi XRING-03 as first adopter — teortaxesTex · 2026-08-25
• Fork of h3.c adds 3090, multi-GPU, GGUF support, and a UI — QuixiAI · 2026-08-25
• 1 hour of AI work now costs less than a minute of SF parking — stuffyokodraws · 2026-08-25
• Qwen 3.8 27B on Mac hits 113 TPS via Dflash2 optimization — TheMoonMidas · 2026-08-25
• TileMix: Tile-Centric Mixed-Precision Attention for LLM Inference — Hanzhi Zhang · 2026-08-25

Infra channel →