MI

Devstral Vision Small 2507

MistralGGUF by QuixiAIUpdated 2025-07-12
Download on Hugging Face
Parameters23.6B
Context128K
Layers40
Architecturellama
Smallest quant11.5 GB
Quick answer

Devstral Vision Small 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 6 quants, from 11.5 GB (Q3_K_M) to 25.1 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Devstral Vision Small 2507 is a 23.6B-parameter Mistral model in GGUF format, quantized by QuixiAI. Its trained context length is 128K tokens. The repository has 6 quant files, from 11.5 GB (Q3_K_M) to 25.1 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M11.5 GB 13.3 GB
Too big Get file →
IQ4_XS12.9 GB 14.7 GB
Too big Get file →
Q4_K_M14.3 GB 16.2 GB
Too big Get file →
Q5_K_M16.8 GB 18.6 GB
Too big Get file →
Q6_K19.3 GB 21.2 GB
Too big Get file →
Q8_025.1 GB 26.9 GB
Too big Get file →

What GPU do you need for Devstral Vision Small 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: 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 IQ4_XS (12.9 GB file, about 14.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (19.3 GB file, about 21.2 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (25.1 GB file, about 26.9 GB in use).

Which Devstral Vision Small 2507 quant should you choose?

Q4_K_M is the usual starting point for Devstral Vision Small 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 Q3_K_M at 11.5 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

Architecturellama
Parameters23.6B
Layers40
Trained context131,072 tokens
KV cache (fp16)160 KB per token

Source

Quantized byQuixiAI
FamilyMistral
Licenseapache-2.0
Downloads (HF)102
Last updated2025-07-12

Frequently asked questions about Devstral Vision Small 2507

How much VRAM does Devstral Vision Small 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 Devstral Vision Small 2507 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Devstral Vision Small 2507 GGUF?

It depends on the quant: Q3_K_M is 11.5 GB, IQ4_XS is 12.9 GB, Q4_K_M is 14.3 GB, Q5_K_M is 16.8 GB, Q6_K is 19.3 GB, Q8_0 is 25.1 GB.

What context length does Devstral Vision Small 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 Devstral Vision Small 2507 GGUF?

The files are on Hugging Face in the QuixiAI/Devstral-Vision-Small-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 Devstral Vision Small 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.

Similar models

Browse all →

More from QuixiAI

All by QuixiAI →

More Mistral models

All Mistral →

Other medium models

All medium models →