Zyphra · First MLX build 9 Nov 2026
ZONOS3-Mini
MLX
Audio apache-2.0 New
A 255M parameter text to speech model from Zyphra, with 2 MLX builds.
- Parameters
- 255M From Hugging Face
- Quantisation
- Unstated ZONOS3-Mini
- Memory needed
- 4 GB Estimate, unified memory
- Download
- 910 MB Weights, estimated
- Downloads
- 255 This build, last 30 days
- Task
- Text to speech Audio
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 4 GB at Unstated
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
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/ZONOS3-MiniMLX builds
2 on mlx-community| ZONOS3-Mini | Unstated | 910 MB | 4 GB | 255 |
|---|---|---|---|---|
| ZONOS3-Mini-swift-ptq | Unstated | — | — | 23 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.