Instructions to use TiGa-RCE/LFM2-1.2B-MLX-oQ-Sweep with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use TiGa-RCE/LFM2-1.2B-MLX-oQ-Sweep with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir LFM2-1.2B-MLX-oQ-Sweep TiGa-RCE/LFM2-1.2B-MLX-oQ-Sweep
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| library_name: mlx | |
| tags: | |
| - mlx | |
| - quantized | |
| - oq | |
| - lfm2 | |
| # LFM2 1.2B MLX oQ Quantization Sweep | |
| This repository is a public preservation archive for locally generated MLX quantizations of [mlx-community/LFM2-1.2B-bf16](https://huggingface.co/mlx-community/LFM2-1.2B-bf16). | |
| ## Provenance | |
| - Source conversion: `mlx-community/LFM2-1.2B-bf16` | |
| - Original model family: `LiquidAI/LFM2-1.2B` | |
| - Quantization: local oMLX/oQ affine MLX safetensors, group size 64 | |
| Each subdirectory is an independently loadable MLX artifact. The directory name is the intended quantization label. Existing standalone `TiGa-RCE/LFM2-1.2B-MLX-oQ4` and `TiGa-RCE/LFM2-1.2B-MLX-oQ8` repositories remain as directly consumable releases; this is the complete archival sweep. | |