This repo contains the full precision source code, in "safe tensors" format to generate GGUFs, GPTQ, EXL2, AWQ, HQQ and other formats. The source code can also be used directly.
TWO monster coders (Mistral's Magistral 24b AND Devstral 24B) in FUSED 75%/75% 36B model configuration ( 62 layers, 561 tensors) with full reasoning (can be turned on/off).
The two best Mistral Coders at 24B in one that are stronger than the sum of their parts.
Full reasoning/thinking which can be turned on or off.
Quick settings below, then info on each model below, AND additional HELP SECTION below these sections.
This model requires:
Settings used for testing (suggested):
BEST settings for coding:
FOR CODING:
Higher temps: .6 to .9 (even over 1) work better for more complex coding / especially with more restrictions.
This model will respond well to both detailed instructions and step by step refinement and additions to code.
As this is an instruct model, it will also benefit from a detailed system prompt too.
For simpler coding problems, lower quants will work well; but for complex/multi-step problem solving suggest Q6 or Q8.
REASONING SYSTEM PROMPT (optional):
A user will ask you to solve a task. You should first draft your thinking process (inner monologue) until you have derived the final answer. Afterwards, write a self-contained summary of your thoughts (i.e. your summary should be succinct but contain all the critical steps you needed to reach the conclusion). You should use Markdown and Latex to format your response. Write both your thoughts and summary in the same language as the task posed by the user.
Your thinking process must follow the template below:
<think>
Your thoughts or/and draft, like working through an exercise on scratch paper. Be as casual and as long as you want until you are confident to generate a correct answer.
</think>
NOTE: Model MAY start reasoning if you use the jinja template (embedded) automatically.
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:
Devstral Small 1.1 is still great when paired with OpenHands. This new version also generalizes better to other prompts and coding environments. 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%.
| 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 |
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.
We recommend to use Devstral with the OpenHands scaffold. You can use it either through our API or by running locally.
Follow these instructions to create a Mistral account and get an API key.
Then run these 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
The model can also be deployed with the following libraries:
vllm (recommended): See heremistral-inference: See heretransformers: See hereLMStudio: See herellama.cpp: See hereollama: See hereInstallation
Make sure you install vLLM >= 0.9.1:
pip install vllm --upgrade
Also make sure to have installed mistral_common >= 1.7.0.
pip install mistral-common --upgrade
To check:
python -c "import mistral_common; print(mistral_common.__version__)"
You can also make use of a ready-to-go docker image or on the docker hub.
Launch server
We recommand that you use Devstral in a server/client setting.
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"])
Installation
Make sure to have mistral_inference >= 1.6.0 installed.
pip install mistral_inference --upgrade
Download
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)
Chat
You can run the model using the following command:
mistral-chat $HOME/mistral_models/Devstral --instruct --max_tokens 300
You can then prompt it with anything you'd like.
mistral-common >= 1.7.0 to use our tokenizer.
pip install mistral-common --upgrade
Then load our tokenizer along with the model and generate:
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)
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/"
You can serve the model locally with LMStudio.
lms cli ~/.lmstudio/bin/lms bootstraplms import Devstral-Small-2507-Q4_K_M.gguf in the directory where you've downloaded the model checkpoint (e.g. Devstral-Small-2507_gguf)Devstral Small 2507. Toggle the status button to start the model, in setting toggle Serve on Local Network to be on.devstral-small-2507 and an api address under API Usage. Keep note of this address, this is used for OpenHands or Cline.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/"
Then run Devstral using the llama.cpp server.
./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.
For additional settings, usage information, benchmarks etc also see:
https://huggingface.co/mistralai/Devstral-Small-2507
Building upon Mistral Small 3.1 (2503), with added reasoning capabilities, undergoing SFT from Magistral Medium traces and RL on top, it's a small, efficient reasoning model with 24B parameters.
Magistral Small can be deployed locally, fitting within a single RTX 4090 or a 32GB RAM MacBook once quantized.
Learn more about Magistral in our blog post.
The model was presented in the paper Magistral.
| Model | AIME24 pass@1 | AIME25 pass@1 | GPQA Diamond | Livecodebench (v5) |
|---|---|---|---|---|
| Magistral Medium | 73.59% | 64.95% | 70.83% | 59.36% |
| Magistral Small | 70.68% | 62.76% | 68.18% | 55.84% |
Please make sure to use:
top_p: 0.95temperature: 0.7max_tokens: 40960We highly recommend including the default system prompt used during RL for the best results, you can edit and customise it if needed for your specific use case.
<s>[SYSTEM_PROMPT]system_prompt
A user will ask you to solve a task. You should first draft your thinking process (inner monologue) until you have derived the final answer. Afterwards, write a self-contained summary of your thoughts (i.e. your summary should be succinct but contain all the critical steps you needed to reach the conclusion). You should use Markdown to format your response. Write both your thoughts and summary in the same language as the task posed by the user. NEVER use \boxed{} in your response.
Your thinking process must follow the template below:
<think>
Your thoughts or/and draft, like working through an exercise on scratch paper. Be as casual and as long as you want until you are confident to generate a correct answer.
</think>
Here, provide a concise summary that reflects your reasoning and presents a clear final answer to the user. Don't mention that this is a summary.
Problem:
[/SYSTEM_PROMPT][INST]user_message[/INST]<think>
reasoning_traces
</think>
assistant_response</s>[INST]user_message[/INST]
system_prompt, user_message and assistant_response are placeholders.
We invite you to choose, depending on your use case and requirements, between keeping reasoning traces during multi-turn interactions or keeping only the final assistant response.
For additional settings, usage information, benchmarks etc also see:
https://huggingface.co/mistralai/Magistral-Small-2506
For more information / other Qwen/Mistral Coders / additional settings see:
[ https://huggingface.co/DavidAU/Qwen2.5-MOE-2x-4x-6x-8x__7B__Power-CODER__19B-30B-42B-53B-gguf ]
CHANGE THE NUMBER OF ACTIVE EXPERTS:
See this document:
https://huggingface.co/DavidAU/How-To-Set-and-Manage-MOE-Mix-of-Experts-Model-Activation-of-Experts
Settings: CHAT / ROLEPLAY and/or SMOOTHER operation of this model:
In "KoboldCpp" or "oobabooga/text-generation-webui" or "Silly Tavern" ;
Set the "Smoothing_factor" to 1.5
: in KoboldCpp -> Settings->Samplers->Advanced-> "Smooth_F"
: in text-generation-webui -> parameters -> lower right.
: In Silly Tavern this is called: "Smoothing"
NOTE: For "text-generation-webui"
-> if using GGUFs you need to use "llama_HF" (which involves downloading some config files from the SOURCE version of this model)
Source versions (and config files) of my models are here:
OTHER OPTIONS:
Increase rep pen to 1.1 to 1.15 (you don't need to do this if you use "smoothing_factor")
If the interface/program you are using to run AI MODELS supports "Quadratic Sampling" ("smoothing") just make the adjustment as noted.
Highest Quality Settings / Optimal Operation Guide / Parameters and Samplers
This a "Class 1" model:
For all settings used for this model (including specifics for its "class"), including example generation(s) and for advanced settings guide (which many times addresses any model issue(s)), including methods to improve model performance for all use case(s) as well as chat, roleplay and other use case(s) please see:
You can see all parameters used for generation, in addition to advanced parameters and samplers to get the most out of this model here: