MI

Devstral Small 2505

MistralGGUF by mistralaiUpdated 2025-07-24
Download on Hugging Face
Parameters23.6B
Context128K
Layers40
Architecturellama
Smallest quant13.4 GB
Quick answer

Devstral Small 2505 needs about 18.6 GB of memory at its main file (a 16.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 5 quants, from 13.4 GB to 47.2 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Devstral Small 2505 – a 24 billion‑parameter agentic coding model

Devstral Small 2505 is a 24 billion‑parameter LLM fine‑tuned for software engineering tasks. It offers a 128k token context window and is text‑only, making it suitable for local deployment on GPUs with 8 GB VRAM or more.

Good at

  • Agentic coding tasks
  • Tool‑based code exploration
  • Multi‑file editing

Limits

  • No vision support
  • Requires 8 GB+ VRAM for full performance
  • Apache‑2.0 license only

Best for

  • Local code assistant
  • Automated code review
  • Software engineering agents

Who it’s for. Developers and teams needing a lightweight, open‑source model for coding tasks. It runs on a single RTX 4090 or a Mac with 32 GB RAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—13.4 GB 15.3 GB
Too big Get file →
—14.3 GB 16.2 GB
Too big Get file →
—16.8 GB 18.6 GB
Too big Get file →
—25.1 GB 26.9 GB
Too big Get file →
—47.2 GB 49.0 GB
Too big Get file →

For 8 GB VRAM use Q4_0 (file size 13.44 GB, estimated 15.3 GB memory). For 16 GB VRAM use Q4_K_M (file size 16.76 GB, estimated 18.6 GB memory). For 24 GB VRAM use Q5_K_M (file size 14.33 GB, estimated 16.2 GB memory).

What GPU do you need for Devstral Small 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: the best quant that fits is the main file (13.4 GB file, about 15.3 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (16.8 GB file, about 18.6 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (25.1 GB file, about 26.9 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (25.1 GB file, about 26.9 GB in use).

Which Devstral Small 2505 quant should you choose?

If memory is tight, the smallest file is the first one in the table at 13.4 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

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

Source

Quantized bymistralai
FamilyMistral
Licenseapache-2.0
Downloads (HF)2,138
Last updated2025-07-24

Frequently asked questions about Devstral Small 2505

How much VRAM does Devstral Small 2505 need?

About 18.6 GB at its main file with an 8K context window. That is the 16.8 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 2505 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Devstral Small 2505 GGUF?

It depends on the quant: file is 13.4 GB, file is 14.3 GB, file is 16.8 GB, file is 25.1 GB, file is 47.2 GB.

What context length does Devstral Small 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 2505 GGUF?

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

Can I run Devstral Small 2505 on an RTX 4090 with 8 GB VRAM?

Yes, using the Q4_0 quantized model which requires about 15.3 GB of VRAM at 8k context.

Does the model support image inputs?

No, the vision encoder was removed; the model is text‑only.

What license applies to this model?

The model is released under the Apache‑2.0 license, allowing commercial and non‑commercial use.

Other GGUFs of Devstral-Small-2505

Similar models

Browse all →

More from mistralai

All by mistralai →

More Mistral models

All Mistral →

Other medium models

All medium models →