Instructions to use jkim96/Devstral-Small-2507-DASHQ-Q2-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 jkim96/Devstral-Small-2507-DASHQ-Q2-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 jkim96/Devstral-Small-2507-DASHQ-Q2-GGUF:IQ2_M
# Run inference directly in the terminal:
llama cli -hf jkim96/Devstral-Small-2507-DASHQ-Q2-GGUF:IQ2_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf jkim96/Devstral-Small-2507-DASHQ-Q2-GGUF:IQ2_M
# Run inference directly in the terminal:
llama cli -hf jkim96/Devstral-Small-2507-DASHQ-Q2-GGUF:IQ2_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf jkim96/Devstral-Small-2507-DASHQ-Q2-GGUF:IQ2_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf jkim96/Devstral-Small-2507-DASHQ-Q2-GGUF:IQ2_M

Use Docker

docker model run hf.co/jkim96/Devstral-Small-2507-DASHQ-Q2-GGUF:IQ2_M

Llama new
LM Studio
Jan

vLLM

How to use jkim96/Devstral-Small-2507-DASHQ-Q2-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jkim96/Devstral-Small-2507-DASHQ-Q2-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jkim96/Devstral-Small-2507-DASHQ-Q2-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jkim96/Devstral-Small-2507-DASHQ-Q2-GGUF:IQ2_M

Ollama
How to use jkim96/Devstral-Small-2507-DASHQ-Q2-GGUF with Ollama:
```
ollama run hf.co/jkim96/Devstral-Small-2507-DASHQ-Q2-GGUF:IQ2_M
```
Unsloth Desktop

How to use jkim96/Devstral-Small-2507-DASHQ-Q2-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jkim96/Devstral-Small-2507-DASHQ-Q2-GGUF:IQ2_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "jkim96/Devstral-Small-2507-DASHQ-Q2-GGUF:IQ2_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use jkim96/Devstral-Small-2507-DASHQ-Q2-GGUF with Docker Model Runner:
```
docker model run hf.co/jkim96/Devstral-Small-2507-DASHQ-Q2-GGUF:IQ2_M
```

Lemonade

How to use jkim96/Devstral-Small-2507-DASHQ-Q2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jkim96/Devstral-Small-2507-DASHQ-Q2-GGUF:IQ2_M

Run and chat with the model

lemonade run user.Devstral-Small-2507-DASHQ-Q2-GGUF-IQ2_M

List all available models

lemonade list

Hermes Agent

How to use jkim96/Devstral-Small-2507-DASHQ-Q2-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jkim96/Devstral-Small-2507-DASHQ-Q2-GGUF:IQ2_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default jkim96/Devstral-Small-2507-DASHQ-Q2-GGUF:IQ2_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use jkim96/Devstral-Small-2507-DASHQ-Q2-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jkim96/Devstral-Small-2507-DASHQ-Q2-GGUF:IQ2_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "jkim96/Devstral-Small-2507-DASHQ-Q2-GGUF:IQ2_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Devstral-Small-2507 - DASH-Q 2-bit GGUF

llama.cpp GGUF files of mistralai/Devstral-Small-2507 quantized with DASH-Q, at several 2-bit-class sizes. Every file uses only standard llama.cpp tensor types (no tensor above 4 bits) and loads in any recent llama.cpp build.

File	Type	Size	Bits / weight
`Devstral-Small-2507-DASHQ-IQ2_XXS.gguf`	IQ2_XXS	6.76 GB	2.29
`Devstral-Small-2507-DASHQ-IQ2_XS.gguf`	IQ2_XS	7.68 GB	2.60
`Devstral-Small-2507-DASHQ-IQ2_M.gguf`	IQ2_M	8.25 GB	2.80
`Devstral-Small-2507-DASHQ-Q2_K_XL.gguf`	Q2_K_XL	9.15 GB	3.10

Perplexity (lower is better)

Type	Model	Size	WikiText-2	C4
IQ2_XXS	llama.cpp IQ2_XXS (imatrix)	6.55 GB	18.83	39.56
IQ2_XXS	unsloth UD-IQ2_XXS	6.75 GB	18.58	37.08
IQ2_XXS	DASH-Q IQ2_XXS	6.76 GB	6.69	11.62
IQ2_XS	llama.cpp IQ2_XS (imatrix)	7.21 GB	13.90	26.11
IQ2_XS	DASH-Q IQ2_XS	7.68 GB	5.99	10.41
IQ2_M	llama.cpp IQ2_M (imatrix)	8.11 GB	8.36	14.51
IQ2_M	unsloth UD-IQ2_M	8.24 GB	8.21	14.04
IQ2_M	DASH-Q IQ2_M	8.25 GB	5.61	9.80
Q2_K_XL	llama.cpp Q2_K (imatrix)	8.89 GB	6.29	10.58
Q2_K_XL	unsloth UD-Q2_K_XL	9.29 GB	6.07	10.25
Q2_K_XL	DASH-Q Q2_K_XL	9.15 GB	5.50	9.61

llama-perplexity, context 2048; WikiText-2 test, C4 validation (256 x 2048 tokens).

Usage

llama-cli -m Devstral-Small-2507-DASHQ-Q2_K_XL.gguf -ngl 99 -c 8192

License

Inherits the license of the base model (mistralai/Devstral-Small-2507).

Downloads last month: 672

GGUF

Model size

24B params

Architecture

llama

Hardware compatibility

2-bit

Model tree for jkim96/Devstral-Small-2507-DASHQ-Q2-GGUF

Base model

mistralai/Mistral-Small-3.1-24B-Base-2503

Finetuned

mistralai/Mistral-Small-3.1-24B-Instruct-2503

Finetuned

mistralai/Devstral-Small-2507

Quantized

(30)

this model