MI

Devstral Small Vision 2505

MistralGGUF by ngxsonUpdated 2025-05-21
Download on Hugging Face
Parameters23.6B
Context128K
Layers40
Architecturellama
Smallest quant14.3 GB
Quick answer

Devstral Small Vision 2505 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. Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Devstral Small Vision 2505 is a 23.6B-parameter Mistral model in GGUF format, quantized by ngxson. Its trained context length is 128K tokens. The repository has 1 quant file, from 14.3 GB (Q4_K_M) to 14.3 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M14.3 GB 16.2 GB
Too big Get file →

What GPU do you need for Devstral Small Vision 2505?

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: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q4_K_M (14.3 GB file, about 16.2 GB in use).

Which Devstral Small Vision 2505 quant should you choose?

Q4_K_M is the usual starting point for Devstral Small Vision 2505: it balances file size and quality well. Here it is a 14.3 GB file.

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 byngxson
FamilyMistral
Licenseapache-2.0
Downloads (HF)132
Last updated2025-05-21

Frequently asked questions about Devstral Small Vision 2505

How much VRAM does Devstral Small Vision 2505 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 Small Vision 2505 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 16.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Devstral Small Vision 2505 GGUF?

It depends on the quant: Q4_K_M is 14.3 GB.

What context length does Devstral Small Vision 2505 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 Small Vision 2505 GGUF?

The files are on Hugging Face in the ngxson/Devstral-Small-Vision-2505-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 Small Vision 2505 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.

Other GGUFs of Devstral-Small-2505

Similar models

Browse all →

More from ngxson

All by ngxson →

More Mistral models

All Mistral →

Other medium models

All medium models →