MiniMaxAI/MiniMax-M3
37 derivatives checked
- amd/MiniMax-M3-MXFP4: Quantization
- MiniMaxAI/MiniMax-M3-MXFP8: Quantization
- nvidia/MiniMax-M3-NVFP4: Quantization
- EmbeddedLLM/MiniMax-M3-FP8-dynamic: Quantization
- unsloth/MiniMax-M3-GGUF: Same weights, converted
- bartowski/MiniMax-M3-GGUF: Quantization
- nvidia/MiniMax-M3-DSpark: Different architecture
- AesSedai/MiniMax-M3-GGUF: Quantization
- spectator2026/MiniMax-M3-AWQ-int4: Quantization
- amd/MiniMax-M3-MXFP4-AttnFP8: Quantization
- kaitchup/MiniMax-M3-GGUF-MoQ: Same weights, converted
- DevQuasar/MiniMaxAI.MiniMax-M3-GGUF: Quantization
- mlx-community/MiniMax-M3-4bit: Quantization
- gghfez/MiniMax-M3-control-vectors: Not comparable yet
- Mapika/MiniMax-M3-NVFP4: Quantization
- ressl/MiniMax-M3-uncensored: Abliterated
- olka-fi/MiniMax-M3-MXFP4: Quantization
- reduxv1/MiniMax-M3-GGUF: Same weights, converted
- OsaurusAI/MiniMax-M3-Coder-Small: Quantization
- sparkarena/Minimax-M3-v0-NVFP4: Quantization
- inferencerlabs/MiniMax-M3-MLX-Q8: Quantization
- prometheusAIR/MiniMax-M3-sm120-safe-GGUF: Quantization
- cyankiwi/MiniMax-M3-AWQ-INT4: Quantization
- SpaceGamer72/MiniMax-M3-uncensored: Abliterated
- Sebesky/MiniMax-M3-W4A16-GPTQ: Quantization
- pipenetwork/MiniMax-M3-MLX-mixed-3_6bit: Quantization
- Sciguy429/MiniMax-M3-MSA-GGUF: Quantization
- pipenetwork/MiniMax-M3-MLX-3bit: Quantization
- lukealonso/MiniMax-M3-NVFP4: Quantization
- unigilby/MiniMax-M3-oQ4: Quantization
15 other repos hold byte-for-byte identical weight files.