chatterbox turbo needs about 1.2 GB of memory at F16 (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 7 quants, from 0.3 GB (Q4_K) to 1.0 GB (F16).
Chatterbox Turbo – 350M‑parameter TTS model with fast generation
Chatterbox Turbo is a 350M‑parameter text‑to‑speech model built on the chatterbox‑s3gen architecture. It delivers high‑quality speech with reduced compute and VRAM compared to earlier models. The model supports paralinguistic tags such as [cough] and [laugh].
Good at
- Fast single‑step mel generation
- Low VRAM usage
- Paralinguistic tag support
Limits
- No vision support
- Requires 8k context for memory estimates
- MIT license only
Best for
- Low‑latency voice agents
- Narration workflows
- Creative audio generation
Who it’s for. Developers building voice assistants or narration tools who need a lightweight TTS model. The model is open‑source under MIT and works with llama.cpp and ggml.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 0.3 GB | 0.8 GB | Fits | Get file → | |
| Q8_0 | 0.4 GB | 0.9 GB | Fits | Get file → | |
| Q4_K | 0.5 GB | 1.0 GB | Fits | Get file → | |
| F16 | 0.7 GB | 1.2 GB | Fits | Get file → | |
| F16 | 0.7 GB | 1.2 GB | Fits | Get file → | |
| Q8_0 | 0.7 GB | 1.2 GB | Fits | Get file → | |
| F16 | 1.0 GB | 1.6 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K (0.26 GB file, ~0.8 GB memory at 8k context). For 12 GB VRAM, Q8_0 (0.37 GB file, ~0.9 GB memory) is suitable. If more memory is available, F16 (0.66 GB file, ~1.2 GB memory) provides higher precision.
What GPU do you need for chatterbox turbo?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is F16 (1.0 GB file, about 1.6 GB in use).
Which chatterbox turbo quant should you choose?
F16 (0.7 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
If memory is tight, the smallest file is Q4_K at 0.3 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about chatterbox turbo
How much VRAM does chatterbox turbo need?
About 1.2 GB at F16 with an 8K context window. That is the 0.7 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run chatterbox turbo on an 8 GB GPU?
Yes, with F16: the 1.0 GB file needs about 1.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of chatterbox turbo GGUF?
It depends on the quant: Q4_K is 0.3 GB, Q8_0 is 0.4 GB, Q4_K is 0.5 GB, F16 is 0.7 GB, F16 is 0.7 GB, Q8_0 is 0.7 GB and 1 more.
Where can I download chatterbox turbo GGUF?
The files are on Hugging Face in the cstr/chatterbox-turbo-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does chatterbox turbo use?
Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Chatterbox Turbo on 8 GB VRAM?
Yes, the Q4_K quantized model requires about 0.8 GB of VRAM at 8k context, which fits within an 8 GB budget.
Does the model support multiple languages?
Yes, it supports Arabic, Danish, German, Greek, English, Spanish, Finnish, French, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese, Russian, Swedish, Swahili, Turkish, and Chinese.