Devstral Small 2507

🚀 Devstral Small 1.1

Devstral is an agentic LLM tailored for software engineering tasks, developed through a collaboration between Mistral AI and All Hands AI 🙌. It excels in leveraging tools to explore codebases, edit multiple files, and empower software engineering agents. The model achieves outstanding performance on SWE-bench, positioning it as the #1 open-source model on this benchmark.

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

For enterprises requiring specialized capabilities (such as increased context or domain-specific knowledge), 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. Refer to the benchmark results for details.
• Devstral Small 1.1 remains excellent when paired with OpenHands. This new version also generalizes better to other prompts and coding environments.
• Supports Mistral's function calling format.

✨ Features

• Agentic Coding: Devstral is designed to excel at agentic coding tasks, making it an ideal choice for software engineering agents.
• Lightweight: With a compact size of just 24 billion parameters, Devstral is lightweight enough to run on a single RTX 4090 or a Mac with 32GB RAM, making it suitable for local deployment and on-device use.
• Apache 2.0 License: An open license that allows 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 outperforms far larger models such as Deepseek-V3-0324 and Qwen3 232B-A22B.

💻 Usage

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

API

Follow these instructions to create a Mistral account and obtain an API key.

Then run the following commands to start the OpenHands docker container:

export MISTRAL_API_KEY=<MY_KEY>

mkdir -p ~/.openhands && echo '{"language":"en","agent":"CodeActAgent","max_iterations":null,"security_analyzer":null,"confirmation_mode":false,"llm_model":"mistral/devstral-small-2507","llm_api_key":"'$MISTRAL_API_KEY'","remote_runtime_resource_factor":null,"github_token":null,"enable_default_condenser":true}' > ~/.openhands-state/settings.json

docker pull docker.all-hands.dev/all-hands-ai/runtime:0.48-nikolaik

docker run -it --rm --pull=always \
    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.48-nikolaik \
    -e LOG_ALL_EVENTS=true \
    -v /var/run/docker.sock:/var/run/docker.sock \
    -v ~/.openhands:/.openhands \
    -p 3000:3000 \
    --add-host host.docker.internal:host-gateway \
    --name openhands-app \
    docker.all-hands.dev/all-hands-ai/openhands:0.48

Local Inference

The model can also be deployed with the following libraries:

• vllm (recommended): See here
• mistral-inference: See here
• transformers: See here
• LMStudio: See here
• llama.cpp: See here
• ollama: See here

vLLM (recommended)

pip install vllm --upgrade

pip install mistral-common --upgrade

python -c "import mistral_common; print(mistral_common.__version__)"

vllm serve mistralai/Devstral-Small-2507 --tokenizer_mode mistral --config_format mistral --load_format mistral --tool-call-parser mistral --enable-auto-tool-choice --tensor-parallel-size 2

import requests
import json
from huggingface_hub import hf_hub_download


url = "http://<your-server-url>:8000/v1/chat/completions"
headers = {"Content-Type": "application/json", "Authorization": "Bearer token"}

model = "mistralai/Devstral-Small-2507"

def load_system_prompt(repo_id: str, filename: str) -> str:
    file_path = hf_hub_download(repo_id=repo_id, filename=filename)
    with open(file_path, "r") as file:
        system_prompt = file.read()
    return system_prompt

SYSTEM_PROMPT = load_system_prompt(model, "SYSTEM_PROMPT.txt")

messages = [
    {"role": "system", "content": SYSTEM_PROMPT},
    {
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": "<your-command>",
            },
        ],
    },
]

data = {"model": model, "messages": messages, "temperature": 0.15}

# Devstral Small 1.1 supports tool calling. If you want to use tools, follow this:
# tools = [ # Define tools for vLLM
#     {
#         "type": "function",
#         "function": {
#             "name": "git_clone",
#             "description": "Clone a git repository",
#             "parameters": {
#                 "type": "object",
#                 "properties": {
#                     "url": {
#                         "type": "string",
#                         "description": "The url of the git repository",
#                     },
#                 },
#                 "required": ["url"],
#             },
#         },
#     }
# ] 
# data = {"model": model, "messages": messages, "temperature": 0.15, "tools": tools} # Pass tools to payload.

response = requests.post(url, headers=headers, data=json.dumps(data))
print(response.json()["choices"][0]["message"]["content"])

Mistral-inference

pip install mistral_inference --upgrade

from huggingface_hub import snapshot_download
from pathlib import Path

mistral_models_path = Path.home().joinpath('mistral_models', 'Devstral')
mistral_models_path.mkdir(parents=True, exist_ok=True)

snapshot_download(repo_id="mistralai/Devstral-Small-2507", allow_patterns=["params.json", "consolidated.safetensors", "tekken.json"], local_dir=mistral_models_path)

mistral-chat $HOME/mistral_models/Devstral --instruct --max_tokens 300

Transformers

pip install mistral-common --upgrade

import torch

from mistral_common.protocol.instruct.messages import (
    SystemMessage, UserMessage
)
from mistral_common.protocol.instruct.request import ChatCompletionRequest
from mistral_common.tokens.tokenizers.mistral import MistralTokenizer
from huggingface_hub import hf_hub_download
from transformers import AutoModelForCausalLM

def load_system_prompt(repo_id: str, filename: str) -> str:
    file_path = hf_hub_download(repo_id=repo_id, filename=filename)
    with open(file_path, "r") as file:
        system_prompt = file.read()
    return system_prompt

model_id = "mistralai/Devstral-Small-2507"
SYSTEM_PROMPT = load_system_prompt(model_id, "SYSTEM_PROMPT.txt")


tokenizer = MistralTokenizer.from_hf_hub(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

tokenized = tokenizer.encode_chat_completion(
    ChatCompletionRequest(
        messages=[
            SystemMessage(content=SYSTEM_PROMPT),
            UserMessage(content="<your-command>"),
        ],
    )
)

output = model.generate(
    input_ids=torch.tensor([tokenized.tokens]),
    max_new_tokens=1000,
)[0]

decoded_output = tokenizer.decode(output[len(tokenized.tokens):])
print(decoded_output)

LM Studio

pip install -U "huggingface_hub[cli]"
huggingface-cli download \
"lmstudio-community/Devstral-Small-2507-GGUF" \ # or mistralai/Devstral-Small-2507_gguf
--include "Devstral-Small-2507-Q4_K_M.gguf" \
--local-dir "Devstral-Small-2507_gguf/"

llama.cpp

pip install -U "huggingface_hub[cli]"
huggingface-cli download \
"mistralai/Devstral-Small-2507_gguf" \
--include "Devstral-Small-2507-Q4_K_M.gguf" \
--local-dir "mistralai/Devstral-Small-2507_gguf/"

./llama-server -m mistralai/Devstral-Small-2507_gguf/Devstral-Small-2507-Q4_K_M.gguf -c 0 # -c configure the context size, 0 means model's default, here 128k.

OpenHands (recommended)

Launch a server to deploy Devstral Small 1.1

Make sure you launched an OpenAI-compatible server such as vLLM or Ollama as described above. Then, you can use OpenHands to interact with Devstral Small 1.1.

In the case of the tutorial, we spun up a vLLM server running the command:

vllm serve mistralai/Devstral-Small-2507 --tokenizer_mode mistral --config_format mistral --load_format mistral --tool-call-parser mistral --enable-auto-tool-choice --tensor-parallel-size 2

The server address should be in the following format: http://<your-server-url>:8000/v1

Launch OpenHands

You can follow the installation of OpenHands here.

The easiest way to launch OpenHands is to use the Docker image:

docker pull docker.all-hands.dev/all-hands-ai/runtime:0.48-nikolaik

docker run -it --rm --pull=always \
    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.48-nikolaik \
    -e LOG_ALL_EVENTS=true \
    -v /var/run/docker.sock:/var/run/docker.sock \
    -v ~/.openhands:/.openhands \
    -p 3000:3000 \
    --add-host host.docker.internal:host-gateway \
    --name openhands-app \
    docker.all-hands.dev/all-hands-ai/openhands:0.48

Then, you can access the OpenHands UI at http://localhost:3000.

Connect to the server

When accessing the OpenHands UI, you will be prompted to connect to a server. You can use the advanced mode to connect to the server you launched earlier.

Fill in the following fields:

• Custom Model: openai/mistralai/Devstral-Small-2507
• Base URL: http://<your-server-url>:8000/v1
• API Key: token (or any other token you used to launch the server if any)

Cline

Launch a server to deploy Devstral Small 1.1

Make sure you launched an OpenAI-compatible server such as vLLM or Ollama as described above. Then, you can use OpenHands to interact with Devstral Small 1.1.

In the case of the tutorial, we spun up a vLLM server running the command:

vllm serve mistralai/Devstral-Small-2507 --tokenizer_mode mistral --config_format mistral --load_format mistral --tool-call-parser mistral --enable-auto-tool-choice --tensor-parallel-size 2

The server address should be in the following format: http://<your-server-url>:8000/v1

Launch Cline

You can follow the installation of Cline here. Then you can configure the server address in the settings.

Examples

OpenHands: Understanding Test Coverage of Mistral Common

We can start the OpenHands scaffold and link it to a repo to analyze test coverage and identify badly covered files. Here we start with our public mistral-common repo.

After the repo is mounted in the workspace, we give the following instruction:

Check the test coverage of the repo and then create a visualization of test coverage. Try plotting a few different types of graphs and save them to a png.

The agent will first browse the code base to check test configuration and structure.

Then it sets up the testing dependencies and launches the coverage test:

Finally, the agent writes the necessary code to visualize the coverage, export the results, and save the plots to a png.

At the end of the run, the following plots are produced:

And the model is able to explain the results:

Cline: Build a Video Game

First, initialize Cline inside VSCode and connect it to the server you launched earlier.

We give the following instruction to build the video game:

Create a video game that mixes Space Invaders and Pong for the web.

Follow these instructions:
- There are two players, one at the top and one at the bottom. The players are controlling a bar to bounce a ball.
- The first player plays with the keys "a" and "d", the second with the right and left arrows.
- The invaders are located at the center of the screen. They should look like the ones in Space Invaders. Their goal is to shoot at the players randomly. They cannot be destroyed by the ball that passes through them. This means that invaders never die.
- The players' goal is to avoid shootings from the space invaders and send the ball to the edge of the other player.
- The ball bounces on the left and right edges.
- Once the ball touches one of the player's edges, the player loses.
- Once a player is touched 3 times or more by a shooting, the player loses.
- The player winning is the last one standing.
- Display on the UI, the number of times a player touched the ball, and the remaining health.

The agent will first create the game:

Then it will explain how to launch the game:

Finally, the game is ready to be played:

Don't hesitate to iterate or give more information to Devstral to improve the game!

📄 License

This project is licensed under the Apache 2.0 license.