Voxtral Small 24B 2507 needs about 16.2 GB of memory at Q4_K_M (a 14.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 27 quants, from 0.0 GB to 47.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
24‑billion‑parameter Voxtral Small with audio and text capabilities
Voxtral Small 24B 2507 is a 24‑billion‑parameter model based on Mistral Small 3.1. It supports vision and audio input, offering speech transcription, translation, and audio understanding. The model retains strong text performance and supports multilingual operation.
Good at
- Speech transcription and translation
- Audio‑based Q&A and summarization
- Multilingual voice interaction
Limits
- No vision support beyond audio
- Requires 32k token context for full audio handling
- Apache‑2.0 license limits commercial use without attribution
Best for
- Transcribing long audio files
- Voice‑controlled function calling
- Multilingual audio summarization
Who it’s for. Developers building voice‑enabled applications that need accurate transcription and multilingual support. Researchers exploring audio‑language models with a 24B parameter backbone.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.9 GB | Fits | Get file → | |
| IQ2_XS | 7.2 GB | 9.0 GB | Too big | Get file → | |
| IQ2_S | 7.5 GB | 9.3 GB | Too big | Get file → | |
| IQ2_M | 8.1 GB | 10.0 GB | Too big | Get file → | |
| Q2_K | 8.9 GB | 10.7 GB | Too big | Get file → | |
| IQ3_XXS | 9.3 GB | 11.1 GB | Too big | Get file → | |
| Q2_K_L | 9.5 GB | 11.4 GB | Too big | Get file → | |
| IQ3_XS | 9.9 GB | 11.7 GB | Too big | Get file → | |
| Q3_K_S | 10.4 GB | 12.2 GB | Too big | Get file → | |
| IQ3_M | 10.7 GB | 12.5 GB | Too big | Get file → | |
| Q3_K_M | 11.5 GB | 13.3 GB | Too big | Get file → | |
| Q3_K_L | 12.4 GB | 14.2 GB | Too big | Get file → | |
| IQ4_XS | 12.8 GB | 14.6 GB | Too big | Get file → | |
| Q3_K_XL | 13.0 GB | 14.8 GB | Too big | Get file → | |
| IQ4_NL | 13.5 GB | 15.3 GB | Too big | Get file → | |
| Q4_0 | 13.5 GB | 15.3 GB | Too big | Get file → | |
| Q4_K_S | 13.5 GB | 15.4 GB | Too big | Get file → | |
| Q4_K_M | 14.3 GB | 16.2 GB | Too big | Get file → | |
| Q4_K_L | 14.8 GB | 16.7 GB | Too big | Get file → | |
| Q4_1 | 14.9 GB | 16.7 GB | Too big | Get file → | |
| Q5_K_S | 16.3 GB | 18.1 GB | Too big | Get file → | |
| Q5_K_M | 16.8 GB | 18.6 GB | Too big | Get file → | |
| Q5_K_L | 17.2 GB | 19.0 GB | Too big | Get file → | |
| Q6_K | 19.3 GB | 21.2 GB | Too big | Get file → | |
| Q6_K_L | 19.7 GB | 21.5 GB | Too big | Get file → | |
| Q8_0 | 25.1 GB | 26.9 GB | Too big | Get file → | |
| BF16 | 47.2 GB | 49.0 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_XS or IQ2_S (≈9 GB memory at 8k context). With 16 GB VRAM, Q4_K_M or Q5_K_S (≈16–18 GB memory). For 32 GB VRAM, Q6_K or Q6_K_L (≈21–22 GB memory). Estimates are approximate.
What GPU do you need for Voxtral Small 24B 2507?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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 the main file (0.0 GB file, about 1.9 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 1.9 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 1.9 GB in use).
- 12 GB VRAM: the best quant that fits is IQ3_XS (9.9 GB file, about 11.7 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_S (13.5 GB file, about 15.4 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K_L (19.7 GB file, about 21.5 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (25.1 GB file, about 26.9 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (25.1 GB file, about 26.9 GB in use).
Which Voxtral Small 24B 2507 quant should you choose?
Q4_K_M is the usual starting point for Voxtral Small 24B 2507: it balances file size and quality well. Here it is a 14.3 GB file.
The Q8_0 file is 25.1 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Voxtral Small 24B 2507
How much VRAM does Voxtral Small 24B 2507 need?
About 16.2 GB at Q4_K_M with an 8K context window. That is the 14.3 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 Small 24B 2507 on an 8 GB GPU?
Yes, with the smaller files: the 0.0 GB file needs about 1.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Voxtral Small 24B 2507 GGUF?
It depends on the quant: file is 0.0 GB, IQ2_XS is 7.2 GB, IQ2_S is 7.5 GB, IQ2_M is 8.1 GB, Q2_K is 8.9 GB, IQ3_XXS is 9.3 GB and 21 more.
What context length does Voxtral Small 24B 2507 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.
Where can I download Voxtral Small 24B 2507 GGUF?
The files are on Hugging Face in the bartowski/mistralai_Voxtral-Small-24B-2507-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 Small 24B 2507 use?
Hugging Face lists the license as apache-2.0. 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 Small 24B 2507 on 8 GB VRAM?
Use the IQ2_XS or IQ2_S quantization; each requires about 9 GB of VRAM at 8k context.
Does this model support image input?
No, the model only supports audio and text input; vision capabilities are not included.
What context length does the model support?
The trained context length is 131,072 tokens, enabling long‑form audio and text processing.