Devstral-Small-2507-Vision-GGUF

<img src="https://huggingface.co/api/resolve-cache/models/EnlistedGhost/Devstral-Small-2507-Vision-GGUF/f6b7c9d3bbd14eb5478c1d46df6f9beca2266d44/resources%2FScreenshot_20251227_232527.png?%2FEnlistedGhost%2FDevstral-Small-2507-Vision-GGUF%2Fresolve%2Fmain%2Fresources%2FScreenshot_20251227_232527.png" alt="Devstral image" width="285" height="168">

-----------------------------------------------<br /> - Model Details and Specifications: -<br />-----------------------------------------------

Devstral Small 2507 Vision GGUF (Ollama & Llama.cpp)

This release contains: <br /> Llama.cpp and Ollama compatible GGUF converted and Quantized model files (Compatible with both Ollama, and Llama.cpp) <br /> (More information and an updates to the ModelCard (this page) coming soon!)

Quantized GGUF version of:

• EnlistedGhost/Devstral-Small-2507-Vision <br /> (by EnlistedGhost)

Original Model Link:

• EnlistedGhost/Devstral-Small-2507-Vision

---

---------------------------------------------------<br /> - Conversion and GGUF Quantization: -<br />---------------------------------------------------

Software used to convert Safetensors to GGUF:

• <a href="https://github.com/ggml-org/llama.cpp/">llama.cpp</a>

Software used to create Quantized GGUF Files:

• <a href="https://github.com/ggml-org/llama.cpp/">llama.cpp</a>

Specific GitHub Commit Point:

• <a href="#">b7266</a>

Converted to GGUF and Quantized by:

• EnlistedGhost

---

-------------------------------<br /> ---- Updates & News ---- <br /> -------------------------------

Model Updates (as of: December 28th, 2025)

• Uploaded: All remaining GGUF Converted and Quantized model files (Q5_K, Q6_K, Q8_0)
• Updated: ModelCard <br /> (this page)

---

--------------------------------------<br /> ---- How to run this Model ---- <br /> --------------------------------------

Compatible Software (Required to use this Model) <br /> You can run this model by using either Ollama (or) Llama.cpp <br /> (Below are instruction on running these GGUF files with Ollama)

How to run this Model using Ollama <br /> You can run this model by using the "ollama run" command.<br /> Simply copy & paste one of the commands from the list below into<br /> your console, terminal or power-shell window.

Vision Projector (Files) <br /> mmproj (Vision Projector) Files

---

---------------------------<br /> ---- Original Info ---- <br /> ---------------------------

(Crossposted from the link in the above section: "Model Details"): <br /> <br />

Devstral Small 1.1

Devstral is an agentic LLM for software engineering tasks built under a collaboration between Mistral AI and All Hands AI 🙌. Devstral excels at using tools to explore codebases, editing multiple files and power software engineering agents. The model achieves remarkable performance on SWE-bench which positions it as the #1 open source model on this benchmark.

It is finetuned from Mistral-Small-3.1, therefore it has a long context window of up to 128k tokens. As a coding agent, Devstral is text-only and before fine-tuning from Mistral-Small-3.1 the vision encoder was removed.

For enterprises requiring specialized capabilities (increased context, domain-specific knowledge, etc.), we will release commercial models beyond what Mistral AI contributes to the community.

Learn more about Devstral in our blog post.

Updates compared to Devstral Small 1.0:

• Improved performance, please refer to the benchmark results.
• Devstral Small 1.1 is still great when paired with OpenHands. This new version also generalizes better to other prompts and coding environments.
• Supports Mistral's function calling format.

Key Features:

• Agentic coding: Devstral is designed to excel at agentic coding tasks, making it a great choice for software engineering agents.
• lightweight: with its compact size of just 24 billion parameters, Devstral is light enough to run on a single RTX 4090 or a Mac with 32GB RAM, making it an appropriate model for local deployment and on-device use.
• Apache 2.0 License: Open license allowing usage and modification for both commercial and non-commercial purposes.
• Context Window: A 128k context window.
• Tokenizer: Utilizes a Tekken tokenizer with a 131k vocabulary size.

Benchmark Results

SWE-Bench

Devstral Small 1.1 achieves a score of 53.6% on SWE-Bench Verified, outperforming Devstral Small 1.0 by +6,8% and the second best state of the art model by +11.4%.

When evaluated under the same test scaffold (OpenHands, provided by All Hands AI 🙌), Devstral exceeds far larger models such as Deepseek-V3-0324 and Qwen3 232B-A22B.

Usage

We recommend to use Devstral with the OpenHands scaffold. You can use it either through our API or by running locally.