ResembleAI · First MLX build 1 Dec 2025
chatterbox
MLX
Audio apache-2.0
A 693M parameter text to speech model from ResembleAI, with 9 MLX builds, from 4-bit to fp16.
- Parameters
- 693M From Hugging Face
- Quantisation
- Unstated chatterbox-multilingual-v3
- Memory needed
- 6 GB Estimate, unified memory
- Download
- 2.7 GB Weights, estimated
- Downloads
- 7.2K This build, last 30 days
- Task
- Text to speech Audio
- MLX builds
- 9 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 6 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/chatterbox-multilingual-v3MLX builds
9 on mlx-community| chatterbox-4bit | 4-bit | 567 MB | 3 GB | 923 |
|---|---|---|---|---|
| chatterbox-5bit | 5-bit | 647 MB | 3 GB | 136 |
| chatterbox-6bit | 6-bit | 727 MB | 3 GB | 172 |
| chatterbox-8bit | 8-bit | 888 MB | 3 GB | 889 |
| Chatterbox-TTS-4bit | 4-bit | 992 MB | 4 GB | 1.9K |
| Chatterbox-TTS-8bit | 8-bit | 1.2 GB | 4 GB | 335 |
| chatterbox-fp16 | fp16 | 2.6 GB | 5 GB | 3.1K |
| Chatterbox-TTS-fp16 | fp16 | 2.7 GB | 6 GB | 1.4K |
| chatterbox-multilingual-v3 | Unstated | 2.7 GB | 6 GB | 7.2K |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.