Voxtral-4B-TTS
By Mistral AI · France
Updated 2026-07-13
Overview
Mistral AI's open frontier TTS model covering 9 languages including French, rivaling ElevenLabs on quality. Note: CC-BY-NC 4.0, non-commercial only.
When to pick this model
- Research and academic TTS projects
- Internal demos and prototypes
- Personal creative work and audiobooks
- Multilingual voice generation with French support
- Offline TTS on a laptop
VRAM requirements by quantization
| Quantization | VRAM required |
|---|---|
| Q4_K_M (recommended) | 10 GB |
| Q5_K_M | 12 GB |
| Q8_0 | 18 GB |
| FP16 (no quantization) | 33 GB |
VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.
In practice, Voxtral-4B-TTS needs a 12 GB card at Q4_K_M (10 GB). Stepping up to Q8_0 nearly doubles the footprint to 18 GB, and unquantized FP16 weights take 33 GB — plan your GPU around the Q4 or Q5 figure unless you specifically need the higher fidelity.
Without a GPU, Voxtral-4B-TTS needs roughly 12 GB of system RAM to run on CPU via llama.cpp or Ollama — workable for background jobs, but far slower than GPU inference. Throughput estimates from our compatibility engine: around 14 tokens/sec on entry-level GPUs, on the order of 40 tokens/sec on a mid-range card, and up to 100 tokens/sec on high-end hardware — assuming the chosen quantization fully fits in VRAM.
What hardware do you need
The table below matches Voxtral-4B-TTS to common GPU memory tiers, using the highest-fidelity quantization that fully fits each card class. Spilling layers to system RAM works but costs most of the speed, so size your card to the quantization you actually want to run.
| GPU memory | Example cards | Best fit for Voxtral-4B-TTS |
|---|---|---|
| 8 GB | RTX 5070 Laptop, RTX 5060, RTX 5060 Ti 8GB | Does not fit — needs 10 GB at Q4_K_M |
| 12 GB | RTX 5070, RTX 5070 Ti Laptop, RTX 4080 Laptop | Q5_K_M (12 GB used) |
| 16 GB | RTX 5080, RTX 4080 Super, Radeon RX 9070 XT | Q5_K_M (12 GB used) |
| 24 GB | RTX 4090, Radeon RX 7900 XTX, RTX 5090 Laptop | Q8_0 (18 GB used) |
| 32 GB | RTX 5090 | Q8_0 (18 GB used) |
Which GPU should you buy to run Voxtral-4B-TTS?
To run Voxtral-4B-TTS locally at Q4, you need ~10 GB of VRAM. The best value for this is a RTX 5070 (12 GB VRAM).
As an Amazon Associate, BestLLMfor earns from qualifying purchases, at no extra cost to you. It does not influence our independent rankings.
Strengths
- Studio-quality TTS in an open model
- Native French alongside 8 other languages
- Runs on consumer laptop hardware
- Competitive with ElevenLabs on quality
Limitations
- CC-BY-NC 4.0 license blocks commercial use
- Not a text LLM, narrower utility
- Short 4K context limits long-form scripts
Typical workloads
In our catalog grid, Voxtral-4B-TTS is filed under FR Voice Synthesis, Voice-over — the use cases where its size/quality trade-off makes the most sense. Its tags translate to concrete workloads: audio understanding; multilingual workloads; French-language output where quality matters.
Note the 4k-token context window — fine for short interactions, limiting for long documents or big retrieval contexts. It ships under the CC-BY-NC 4.0 license — commercial use is generally possible but read the specific terms before embedding it in a product.
Architecture & training
Architecture: Open frontier TTS · 4B · 9 languages
Training: Direct competitor to ElevenLabs.
An ElevenLabs-class TTS for non-commercial work; commercial users need a different license path.
Quick start
# HuggingFace : mistralai/Voxtral-4B-TTS-2603Or use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.
Similar models worth comparing
Frequently asked questions
How much VRAM does Voxtral-4B-TTS need?
At the recommended Q4_K_M quantization, Voxtral-4B-TTS needs about 10 GB of VRAM. Q8_0 takes 18 GB, and unquantized FP16 weights take 33 GB.
Can Voxtral-4B-TTS run without a GPU?
Yes — with roughly 12 GB of system RAM it runs CPU-only through llama.cpp or Ollama. Expect a fraction of GPU speed, which is fine for background or batch jobs but slow for interactive chat.
What context window does Voxtral-4B-TTS support?
Voxtral-4B-TTS supports a 4k-token context window (4,096 tokens).
Can I use Voxtral-4B-TTS commercially?
Voxtral-4B-TTS ships under the CC-BY-NC 4.0 license. Commercial use is generally permitted subject to its terms — review the license text before shipping a product.
How fast is Voxtral-4B-TTS on consumer hardware?
Our compatibility engine estimates on the order of 40 tokens/sec on a mid-range GPU and up to 100 tokens/sec on high-end cards, assuming the quantization fully fits in VRAM.
Which quantization of Voxtral-4B-TTS should I download first?
Start with Q4_K_M (10 GB) — the standard size/quality sweet spot. Step up to Q5_K_M or Q8_0 only if you have VRAM headroom. On a 24 GB card you can run up to Q8_0.