Instructions to use flyingfishinwater/mlxmodels with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use flyingfishinwater/mlxmodels with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir mlxmodels flyingfishinwater/mlxmodels
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Ctrl+K
- Bonsai-4B-mlx-1bit
- GLM-OCR-4bit-mlx
- LFM2.5-1.2B-Instruct-MLX-4bit
- LFM2.5-2.6B-4bit
- LFM2.5-8B-A1B-MLX-4bit
- LFM2.5-VL-1.6B-4bit
- LFM2.5-VL-3B-MLX-4bit
- MiniCPM5-1B-4bit
- Ministral-3-3B-Instruct-2512-4bit
- Qwen3.5-0.8B-MLX-4bit
- Qwen3.5-2B-MLX-4bit
- Qwen3.5-4B-MLX-4bit
- Ternary-Bonsai-1.7B-mlx-2bit
- Ternary-Bonsai-4B-mlx-2bit
- Ternary-Bonsai-8B-mlx-2bit
- gemma-4-e2b-it-4bit
- granite-4.2-3b-MLX-4bit
- 2.57 kB
- 3.41 kB