Instructions to use sibus3/Kokoro-82M-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use sibus3/Kokoro-82M-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download sibus3/Kokoro-82M-mlx --local-dir Kokoro-82M-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Kokoro-82M β MLX conversion
MLX (Apple Silicon) conversion of
hexgrad/Kokoro-82M for use with
the kokoro_mlx package.
kokoro-v1_0.mlx.safetensorsβ model weights, 413 tensors, format-converted only (no fine-tuning)voices/*.safetensorsβ all 54 upstream voices pre-converted to MLX safetensors (torch-free loading)config.jsonβ upstream config, unmodified
The original model and voices are by hexgrad, licensed Apache-2.0; this repo redistributes them in converted form under the same license.
- Downloads last month
- 44
Hardware compatibility
Log In to add your hardware
Quantized
Inference Providers NEW
This model isn't deployed by any Inference Provider. π Ask for provider support