MiniMaxAI/MiniMax-M2.5
36 derivatives checked
- lmstudio-community/MiniMax-M2.5-MLX-8bit: Different architecture
- togethercomputer/Aurora-Spec-Minimax-M2.5: Quantization
- lmstudio-community/MiniMax-M2.5-MLX-4bit: Different architecture
- lmstudio-community/MiniMax-M2.5-MLX-6bit: Different architecture
- nvidia/MiniMax-M2.5-NVFP4: Different architecture
- unsloth/MiniMax-M2.5-GGUF: Quantization
- mudler/MiniMax-M2.5-APEX-GGUF: Quantization
- thoughtworks/MiniMax-M2.5-Eagle3: Quantization
- mradermacher/MiniMax-M2.5-i1-GGUF: Quantization
- lmstudio-community/MiniMax-M2.5-GGUF: Quantization
- dealignai/MiniMax-M2.5-UNCENSORED-JANG_2L: Different architecture
- DevQuasar/MiniMaxAI.MiniMax-M2.5-GGUF: Quantization
- ubergarm/MiniMax-M2.5-GGUF: Quantization
- Intel/MiniMax-M2.5-int4-AutoRound: Different architecture
- cyankiwi/MiniMax-M2.5-AWQ-4bit: Different architecture
- mradermacher/MiniMax-M2.5-GGUF: Quantization
- mratsim/MiniMax-M2.5-FP8-INT4-AWQ: Different architecture
- yujiepan/minimax-m2.5-tiny-random: Quantization
- QuantPasture/MiniMax-M2.5-GGUF: Quantization
- Iambackup/MiniMax-M2.5-UNCENSORED-JANG_2L: Different architecture
- marksverdhei/MiniMax-M2.5-GGUF: Quantization
- QuantTrio/MiniMax-M2.5-AWQ: Different architecture
- Ishowbackup/MiniMax-M2.5-UNCENSORED-JANG_2L: Different architecture
- cerebras/MiniMax-M2.5-REAP-139B-A10B: Partial fine-tune (fewer layers)
- selimaktas/MiniMax-M2.75-460B-A20B: Full fine-tune (fewer layers)
- mlx-community/MiniMax-M2.5-3bit: Different architecture
- cerebras/MiniMax-M2.5-REAP-172B-A10B: Partial fine-tune
- lukealonso/MiniMax-M2.5-NVFP4: Different architecture
- Ex0bit/MiniMax-SLURPY: Full fine-tune
- RedHatAI/MiniMax-M2.5-NVFP4: Different architecture
34 other repos hold byte-for-byte identical weight files.