Instructions to use Kentucky-Open-Science/LFM3-Audio-2B-MLX-3bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use Kentucky-Open-Science/LFM3-Audio-2B-MLX-3bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download Kentucky-Open-Science/LFM3-Audio-2B-MLX-3bit --local-dir LFM3-Audio-2B-MLX-3bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Commit History
8 days ago
-
Add LFM3 Audio 2B MLX 3-bit model
Verified signaturePublish affine 3-bit language-backbone quantization (group size 64), original speech codec and tokenizer, source license, modification notices, model card, dependency lock, and checksums. Source: LiquidAI/LFM3-Audio-2B-MLX-bf16 revision 452469a1afe66dd4932d0e9237603229fa606c0d. Validated with MLX Audio 0.6.5 and MLX 0.32.4 on Python 3.12.65619d4