voxtral 4b tts needs about 5.4 GB of memory at Q8_0 (a 4.3 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 2.4 GB (Q4_K) to 8.2 GB (F16).
Voxtral 4B TTS – 4 billion‑parameter text‑to‑speech model
Voxtral 4B TTS delivers realistic, expressive speech across nine languages. It supports 20 preset voices and offers low‑latency generation with 24 kHz audio output. The model is released under CC‑BY‑NC‑4.0.
Good at
- Realistic multilingual TTS
- Low‑latency inference
- Preset voice adaptation
Limits
- No vision support
- CC‑BY‑NC‑4.0 license limits commercial use
- Requires 8 k context for estimates
Best for
- Voice agents in customer support
- Real‑time translation services
- Automotive in‑vehicle voice systems
Who it’s for. Developers building production‑ready voice agents who need expressive, multilingual speech. The model is suitable for non‑commercial projects due to its CC‑BY‑NC‑4.0 license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 2.4 GB | 3.1 GB | Fits | Get file → | |
| Q8_0 | 4.3 GB | 5.4 GB | Fits | Get file → | |
| F16 | 8.2 GB | 9.6 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K (2.35 GB file, ~3.1 GB memory). For 16 GB VRAM, Q8_0 (4.35 GB file, ~5.4 GB memory) offers higher precision. If 32 GB VRAM is available, F16 (8.17 GB file, ~9.6 GB memory) provides full‑precision weights.
What GPU do you need for voxtral 4b tts?
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 Q4_K (2.4 GB file, about 3.1 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 5.4 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 5.4 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (8.2 GB file, about 9.6 GB in use).
Which voxtral 4b tts quant should you choose?
Q8_0 (4.3 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
If memory is tight, the smallest file is Q4_K at 2.4 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 voxtral 4b tts
How much VRAM does voxtral 4b tts need?
About 5.4 GB at Q8_0 with an 8K context window. That is the 4.3 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 voxtral 4b tts on an 8 GB GPU?
Yes, with Q8_0: the 4.3 GB file needs about 5.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of voxtral 4b tts GGUF?
It depends on the quant: Q4_K is 2.4 GB, Q8_0 is 4.3 GB, F16 is 8.2 GB.
Where can I download voxtral 4b tts GGUF?
The files are on Hugging Face in the cstr/voxtral-4b-tts-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 voxtral 4b tts use?
Hugging Face lists the license as cc-by-nc-4.0. 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 Voxtral 4B TTS on 8 GB VRAM?
Yes, the Q4_K quantization requires about 3.1 GB of VRAM at 8 k context, which fits within 8 GB.
Does this model support voice customization?
The model includes 20 preset voices and allows adaptation to new voices via the voice prefix feature.
Is the model suitable for commercial use?
No, the CC‑BY‑NC‑4.0 license restricts commercial deployment.