Voxtral Small 24B 2507 needs about 18.3 GB of memory at Q4_K_M (a 15.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 6 quants, from 10.4 GB (Q3_K) to 25.8 GB (Q8_0).
Voxtral Small 24B 2507 is a 24.3B-parameter Mistral model in GGUF format, quantized by andrijdavid. The repository has 6 quant files, from 10.4 GB (Q3_K) to 25.8 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K | 10.4 GB | 12.2 GB | Too big | Get file → | |
| Q4_0 | 13.7 GB | 15.8 GB | Too big | Get file → | |
| Q4_K_M | 15.9 GB | 18.3 GB | Too big | Get file → | |
| Q5_K | 16.7 GB | 19.2 GB | Too big | Get file → | |
| Q6_K | 19.9 GB | 22.8 GB | Too big | Get file → | |
| Q8_0 | 25.8 GB | 29.4 GB | Too big | Get file → |
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 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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is Q4_0 (13.7 GB file, about 15.8 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (19.9 GB file, about 22.8 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (25.8 GB file, about 29.4 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 15.9 GB file.
The Q8_0 file is 25.8 GB, about 1.6 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 Q3_K at 10.4 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
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 18.3 GB at Q4_K_M with an 8K context window. That is the 15.9 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?
Not at an 8K context. The smallest file needs about 12.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Voxtral Small 24B 2507 GGUF?
It depends on the quant: Q3_K is 10.4 GB, Q4_0 is 13.7 GB, Q4_K_M is 15.9 GB, Q5_K is 16.7 GB, Q6_K is 19.9 GB, Q8_0 is 25.8 GB.
Where can I download Voxtral Small 24B 2507 GGUF?
The files are on Hugging Face in the andrijdavid/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.