---
base_model: mistralai/Devstral-Small-2507
pipeline_tag: text-generation
inference: true
language:
- en
license: apache-2.0
model_creator: mistralai
model_name: Devstral-Small-2507
model_type: mistral
quantized_by: brittlewis12
tags:
- devstral
- coding
- mistral
---
# Devstral Small 1.1 GGUF
**Original model**: [Devstral Small 1.1](https://huggingface.co/mistralai/Devstral-Small-2507)
**Model creator**: [Mistral AI](https://huggingface.co/mistralai)
> Devstral is an agentic LLM for software engineering tasks built under a collaboration between [Mistral AI](https://mistral.ai/) and [All Hands AI](https://www.all-hands.dev/) 🙌. 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 positionates it as the #1 open source model on this benchmark.
>
> It is finetuned from [Mistral-Small-3.1](https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Base-2503), 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.
This repo contains GGUF format model files for Mistral AI's _Devstral Small 1.1 (2507)_. Read more on Mistral’s [announcement blog post](https://mistral.ai/news/devstral-2507).
---
### What is GGUF?
GGUF is a file format for representing AI models. It is the third version of the format,
introduced by the ggml-org team on August 21st 2023.
Converted with llama.cpp build b5864 (revision [11ee0fe](https://github.com/ggml-org/llama.cpp/commits/11ee0fea2a24da1d3206eeba8fc52b759d9dfb24)), using [autogguf-rs](https://github.com/brittlewis12/autogguf-rs).
---
### Chat template: [Mistral 3 (v7-Tekken)](https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501#basic-instruct-template-v7-tekken)
```
[SYSTEM_PROMPT]{{system_message}}[/SYSTEM_PROMPT]
[INST]{{prompt}}[/INST]
{{assistant_response}}
```
---
## Download & run with [cnvrs](https://twitter.com/cnvrsai) on iPhone, iPad, and Mac!
[cnvrs](https://testflight.apple.com/join/sFWReS7K) is the best app for private, local AI on your device:
- create & save **Characters** with custom system prompts & temperature settings
- download and experiment with any **GGUF model** you can [find on HuggingFace](https://huggingface.co/models?library=gguf)!
* or, use an API key with the chat completions-compatible model provider of your choice -- ChatGPT, Claude, Gemini, DeepSeek, & more!
- make it your own with custom **Theme colors**
- powered by Metal ⚡️ & [Llama.cpp](https://github.com/ggml-org/llama.cpp), with **haptics** during response streaming!
- **try it out** yourself today, on [Testflight](https://testflight.apple.com/join/sFWReS7K)!
* if you **already have the app**, download Devstral Small 2507 now!
*
- follow [cnvrs on twitter](https://twitter.com/cnvrsai) to stay up to date
---
## Original Model Evaluation
| Model | Agentic Scaffold | SWE-Bench Verified (%) |
|--------------------|--------------------|------------------------|
| Devstral Small 1.1 | OpenHands Scaffold | **53.6** |
| Devstral Small 1.0 | OpenHands Scaffold | *46.8* |
| GPT-4.1-mini | OpenAI Scaffold | 23.6 |
| Claude 3.5 Haiku | Anthropic Scaffold | 40.6 |
| SWE-smith-LM 32B | SWE-agent Scaffold | 40.2 |
| Skywork SWE | OpenHands Scaffold | 38.0 |
| DeepSWE | R2E-Gym Scaffold | 42.2 |