MLX
Safetensors
minimax_m2
quantized
mixed-precision
minimax
Mixture of Experts
custom_code
4-bit precision
Instructions to use baa-ai/MiniMax-M2.5-RAM-120GB-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use baa-ai/MiniMax-M2.5-RAM-120GB-MLX with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir MiniMax-M2.5-RAM-120GB-MLX baa-ai/MiniMax-M2.5-RAM-120GB-MLX
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
Ctrl+K
- 1.57 kB
- 2.32 kB
- 6.52 kB
- 94.6 kB
- 10.2 kB
- 166 Bytes
- 5.03 GB xet
- 5.1 GB xet
- 5.33 GB xet
- 5.34 GB xet
- 5.07 GB xet
- 5.34 GB xet
- 5.08 GB xet
- 5.34 GB xet
- 5.15 GB xet
- 5.35 GB xet
- 5.17 GB xet
- 5.09 GB xet
- 4.79 GB xet
- 5 GB xet
- 5.09 GB xet
- 5.09 GB xet
- 5 GB xet
- 5.09 GB xet
- 5.09 GB xet
- 5 GB xet
- 4.94 GB xet
- 3.04 GB xet
- 151 kB
- 30.9 kB
- 15.5 MB xet
- 1.38 kB