MiniMaxAI/MiniMax-M2.1
19 derivatives checked
- unsloth/MiniMax-M2.1-GGUF: Quantization
- mlx-community/MiniMax-M2.1-4bit: Different architecture
- mradermacher/MiniMax-M2.1-i1-GGUF: Quantization
- bartowski/MiniMaxAI_MiniMax-M2.1-GGUF: Quantization
- amd/MiniMax-M2.1-MXFP4: Different architecture
- mlx-community/MiniMax-M2.1-3bit: Different architecture
- mradermacher/MiniMax-M2.1-GGUF: Quantization
- AaryanK/MiniMax-M2.1-GGUF: Quantization
- DevQuasar/MiniMaxAI.MiniMax-M2.1-GGUF: Quantization
- John1604/MiniMax-M2.1-gguf: Quantization
- mlx-community/MiniMax-M2.1-8bit: Different architecture
- cerebras/MiniMax-M2.1-REAP-139B-A10B: Partial fine-tune (fewer layers)
- Ex0bit/MiniMax-M2.1-PRISM: Quantization
- QuantTrio/MiniMax-M2.1-AWQ: Different architecture
- cerebras/MiniMax-M2.1-REAP-172B-A10B: Partial fine-tune
- cyankiwi/MiniMax-M2.1-AWQ-4bit: Different architecture
- mratsim/MiniMax-M2.1-FP8-INT4-AWQ: Different architecture
- 0xSero/MiniMax-M2.1-139B: Partial fine-tune (fewer layers)
- 0xSero/MiniMax-M2.1-162B: Partial fine-tune
4 other repos hold byte-for-byte identical weight files.