Instructions to use brittlewis12/Devstral-Small-2507-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use brittlewis12/Devstral-Small-2507-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf brittlewis12/Devstral-Small-2507-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf brittlewis12/Devstral-Small-2507-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf brittlewis12/Devstral-Small-2507-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf brittlewis12/Devstral-Small-2507-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf brittlewis12/Devstral-Small-2507-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf brittlewis12/Devstral-Small-2507-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf brittlewis12/Devstral-Small-2507-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf brittlewis12/Devstral-Small-2507-GGUF:Q4_K_M

Use Docker

docker model run hf.co/brittlewis12/Devstral-Small-2507-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use brittlewis12/Devstral-Small-2507-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "brittlewis12/Devstral-Small-2507-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "brittlewis12/Devstral-Small-2507-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/brittlewis12/Devstral-Small-2507-GGUF:Q4_K_M

Ollama
How to use brittlewis12/Devstral-Small-2507-GGUF with Ollama:
```
ollama run hf.co/brittlewis12/Devstral-Small-2507-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use brittlewis12/Devstral-Small-2507-GGUF with Docker Model Runner:
```
docker model run hf.co/brittlewis12/Devstral-Small-2507-GGUF:Q4_K_M
```

Lemonade

How to use brittlewis12/Devstral-Small-2507-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull brittlewis12/Devstral-Small-2507-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Devstral-Small-2507-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

Devstral-Small-2507-GGUF / README.md

brittlewis12

Update README.md

036a4aa verified about 1 year ago

preview code

Raw

History Blame Contribute Delete

3.79 kB

	---
	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)

	```
	<s>[SYSTEM_PROMPT]{{system_message}}[/SYSTEM_PROMPT]

	[INST]{{prompt}}[/INST]
	{{assistant_response}}</s>


	```

	---

	## Download & run with [cnvrs](https://twitter.com/cnvrsai) on iPhone, iPad, and Mac!

	![cnvrs.ai](https://pbs.twimg.com/profile_images/1744049151241797632/0mIP-P9e_400x400.jpg)

	[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!
	* <cnvrsai:///models/search/hf?id=brittlewis12/devstral-small-2507-GGUF>
	- 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 \|