MLX Community · First MLX build 28 Feb 2025
Kokoro-82M
MLX
Audio apache-2.0 Trending
A text to speech model, with 4 MLX builds, from bf16 to 6-bit.
- Parameters
- — Not published
- Quantisation
- bf16 Kokoro-82M-bf16
- Memory needed
- — GB Estimate, unified memory
- Download
- — Weights, estimated
- Downloads
- 52K This build, last 30 days
- Task
- Text to speech Audio
- MLX builds
- 4 On mlx-community
- Devices
- Mac Apple silicon
Memory
Hugging Face does not list a weights size for this build, so there is no memory estimate.
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/Kokoro-82M-bf16MLX builds
4 on mlx-community| Kokoro-82M-bf16 | bf16 | — | — | 52K |
|---|---|---|---|---|
| Kokoro-82M-8bit | 8-bit | — | — | 1.6K |
| Kokoro-82M-4bit | 4-bit | — | — | 792 |
| Kokoro-82M-6bit | 6-bit | — | — | 143 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.