Instructions to use anquachdev/hibiki-1b-mlx-q4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use anquachdev/hibiki-1b-mlx-q4 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir hibiki-1b-mlx-q4 anquachdev/hibiki-1b-mlx-q4
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
metadata
license: cc-by-4.0
language:
- fr
- en
base_model: kyutai/hibiki-1b-mlx-bf16
base_model_relation: quantized
tags:
- hibiki
- mlx
- speech-to-speech
- quantized
Hibiki 1B MLX Q4
Weight-only quantization of the language model from the artifact revision unknown.
- Quantization: Q4, group size 32
- Quantized modules: compatible MLX Linear layers only
- Unchanged: Mimi codec, embeddings, normalisation layers, tokenizer