4-bit Open on Hugging Face
Parameters
680M
Weights (est.)
≈ 992 MB
Mac memory (est.)
8 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Details
- Base model
- ResembleAI/chatterbox (finetune)
- Vendor
- ResembleAI
- Task
- Text to speech
- Quantisation
- 4-bit
- Licence
- —
- Downloads
- 1.9K in the last 30 days · 4.9K all time · 3 likes
- Published
- 2025-12-01 · updated 2025-12-05 (11mo ago)
- Tags
- mlx-audio-plus, chatterbox
Other MLX builds of ResembleAI/chatterbox
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| chatterbox-4bit | 4-bit | ≈ 567 MB | 8 GB+ | 918 |
| chatterbox-5bit | 5-bit | ≈ 647 MB | 8 GB+ | 124 |
| chatterbox-6bit | 6-bit | ≈ 727 MB | 8 GB+ | 157 |
| chatterbox-8bit | 8-bit | ≈ 888 MB | 8 GB+ | 864 |
| Chatterbox-TTS-4bit (this one) | 4-bit | ≈ 992 MB | 8 GB+ | 1.9K |
| Chatterbox-TTS-8bit | 8-bit | ≈ 1.2 GB | 8 GB+ | 315 |
| chatterbox-fp16 | fp16 | ≈ 2.6 GB | 8 GB+ | 3.1K |
| Chatterbox-TTS-fp16 | fp16 | ≈ 2.7 GB | 8 GB+ | 1.4K |
| chatterbox-multilingual-v3 | — | ≈ 2.7 GB | 8 GB+ | 7.1K |