kyutai · First MLX build 18 Jan 2026
pocket-tts
MLX
Audio cc-by-4.0
A 118M parameter text to speech model from kyutai, with 4 MLX builds, from 4-bit to 8-bit.
- Parameters
- 118M From Hugging Face
- Quantisation
- Unstated pocket-tts
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 236 MB Weights, estimated
- Downloads
- 1.5K This build, last 30 days
- Task
- Text to speech Audio
- MLX builds
- 4 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 3 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/pocket-ttsMLX builds
4 on mlx-community| pocket-tts-4bit | 4-bit | 89 MB | 3 GB | 105 |
|---|---|---|---|---|
| pocket-tts-6bit | 6-bit | 115 MB | 3 GB | 26 |
| pocket-tts-8bit | 8-bit | 140 MB | 3 GB | 116 |
| pocket-tts | Unstated | 236 MB | 3 GB | 1.5K |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.