MiniMaxAI/MiniMax-M2
22 derivatives checked
- unsloth/MiniMax-M2-GGUF: Quantization
- lmstudio-community/MiniMax-M2-MLX-8bit: Different architecture
- lmstudio-community/MiniMax-M2-MLX-4bit: Different architecture
- lmstudio-community/MiniMax-M2-MLX-6bit: Different architecture
- bartowski/MiniMaxAI_MiniMax-M2-GGUF: Quantization
- tiny-random/minimax-m2: Quantization
- QuantTrio/MiniMax-M2-AWQ: Different architecture
- DevQuasar/MiniMaxAI.MiniMax-M2-GGUF: Quantization
- lmstudio-community/MiniMax-M2-GGUF: Quantization
- yujiepan/minimax-m2-tiny-random: Quantization
- mlx-community/MiniMax-M2-4bit: Different architecture
- lemuralabs/MiniMax-M2-Pruned-25: Quantization
- OsaurusAI/MiniMax-M2.7-Small-JANGTQ: Different architecture
- redponike/MiniMax-M2-GGUF: Quantization
- cturan/MiniMax-M2-GGUF: Quantization
- bullerwins/MiniMax-M2-GGUF: Quantization
- cerebras/MiniMax-M2-REAP-162B-A10B: Partial fine-tune
- cerebras/MiniMax-M2-REAP-139B-A10B: Partial fine-tune (fewer layers)
- cerebras/MiniMax-M2-REAP-172B-A10B: Partial fine-tune
- moxin-org/MiniMax-M2-GGUF: Quantization
- ilintar/MiniMax-M2-GGUF: Quantization
- lemuralabs/MiniMax-M2-Pruned-55: Quantization
6 other repos hold byte-for-byte identical weight files.