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 MOE (Mixture of Experts) 2x24B configuration 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.
Both models code together, with Magistral in "charge" using Devstral's coding power.
Full reasoning/thinking which can be turned on or off.
If you want a version where "Devstral" is in charge (but still have reasoning on/off + Magistral) see this repo:
https://huggingface.co/DavidAU/Mistral-2x24B-MOE-Power-Devstral-Magistral-Reasoning-Ultimate-44B
Info on each model below, info on MOE model / settings etc below this.
GGUF (enhanced, NEO Imatrix:)
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 positionates 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.
Devstral achieves a score of 46.8% on SWE-Bench Verified, outperforming prior open-source SoTA by 6%.
| Model | Scaffold | SWE-Bench Verified (%) |
|---|---|---|
| Devstral | 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 |
For additional settings, usage information, benchmarks etc also see:
https://huggingface.co/mistralai/Devstral-Small-2505
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
SETTINGS
Max context is 128k/131072 ; for reasoning strongly suggest min 8k context window, if reasoning is on.
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>
GENERAL:
All versions have default of 2 experts activated.
Number of active experts can be adjusted in Lmstudio and other AI Apps.
Suggest 2-4 generations, especially if using 1 expert (all models).
Models will accept "simple prompt" as well as very detailed instructions ; however for larger projects I suggest using Q6/Q8 quants / optimized quants.
Suggested Settings :
For additional settings, usage information, benchmarks etc also see:
https://huggingface.co/mistralai/Devstral-Small-2505
and/or
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: