Instructions to use FreedomAISVR/Devstral-Small-2-NVFP4-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FreedomAISVR/Devstral-Small-2-NVFP4-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="FreedomAISVR/Devstral-Small-2-NVFP4-GGUF",
	filename="devstral-small-2-nvfp4.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use FreedomAISVR/Devstral-Small-2-NVFP4-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 FreedomAISVR/Devstral-Small-2-NVFP4-GGUF:NVFP4
# Run inference directly in the terminal:
llama cli -hf FreedomAISVR/Devstral-Small-2-NVFP4-GGUF:NVFP4

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf FreedomAISVR/Devstral-Small-2-NVFP4-GGUF:NVFP4
# Run inference directly in the terminal:
llama cli -hf FreedomAISVR/Devstral-Small-2-NVFP4-GGUF:NVFP4

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 FreedomAISVR/Devstral-Small-2-NVFP4-GGUF:NVFP4
# Run inference directly in the terminal:
./llama-cli -hf FreedomAISVR/Devstral-Small-2-NVFP4-GGUF:NVFP4

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 FreedomAISVR/Devstral-Small-2-NVFP4-GGUF:NVFP4
# Run inference directly in the terminal:
./build/bin/llama-cli -hf FreedomAISVR/Devstral-Small-2-NVFP4-GGUF:NVFP4

Use Docker

docker model run hf.co/FreedomAISVR/Devstral-Small-2-NVFP4-GGUF:NVFP4

LM Studio
Jan

vLLM

How to use FreedomAISVR/Devstral-Small-2-NVFP4-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FreedomAISVR/Devstral-Small-2-NVFP4-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": "FreedomAISVR/Devstral-Small-2-NVFP4-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/FreedomAISVR/Devstral-Small-2-NVFP4-GGUF:NVFP4

Ollama
How to use FreedomAISVR/Devstral-Small-2-NVFP4-GGUF with Ollama:
```
ollama run hf.co/FreedomAISVR/Devstral-Small-2-NVFP4-GGUF:NVFP4
```

Unsloth Studio

How to use FreedomAISVR/Devstral-Small-2-NVFP4-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for FreedomAISVR/Devstral-Small-2-NVFP4-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for FreedomAISVR/Devstral-Small-2-NVFP4-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for FreedomAISVR/Devstral-Small-2-NVFP4-GGUF to start chatting

How to use FreedomAISVR/Devstral-Small-2-NVFP4-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf FreedomAISVR/Devstral-Small-2-NVFP4-GGUF:NVFP4

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "FreedomAISVR/Devstral-Small-2-NVFP4-GGUF:NVFP4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use FreedomAISVR/Devstral-Small-2-NVFP4-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 FreedomAISVR/Devstral-Small-2-NVFP4-GGUF:NVFP4

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 FreedomAISVR/Devstral-Small-2-NVFP4-GGUF:NVFP4

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use FreedomAISVR/Devstral-Small-2-NVFP4-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf FreedomAISVR/Devstral-Small-2-NVFP4-GGUF:NVFP4

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 "FreedomAISVR/Devstral-Small-2-NVFP4-GGUF:NVFP4" \
  --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"

Docker Model Runner
How to use FreedomAISVR/Devstral-Small-2-NVFP4-GGUF with Docker Model Runner:
```
docker model run hf.co/FreedomAISVR/Devstral-Small-2-NVFP4-GGUF:NVFP4
```

Lemonade

How to use FreedomAISVR/Devstral-Small-2-NVFP4-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull FreedomAISVR/Devstral-Small-2-NVFP4-GGUF:NVFP4

Run and chat with the model

lemonade run user.Devstral-Small-2-NVFP4-GGUF-NVFP4

List all available models

lemonade list

Devstral-Small-2-NVFP4-GGUF

GGUF quantization of mistralai/Devstral-Small-2-24B-Instruct-2512 — a 24B dense multimodal coding model built on Mistral-Small-3.1 with 393K context, vision support, and tool calling.

Quantized to NVFP4 format for efficient inference with minimal quality loss.

About NVFP4

NVFP4 is NVIDIA's native 4-bit floating-point format (E4M3) for Blackwell GPUs. It stores weights in FP4 with a shared per-block scale, enabling native Blackwell tensor core acceleration with no dequantization overhead during inference.

Files

Filename	Type	Size	Description
`devstral-small-2-nvfp4.gguf`	GGUF (NVFP4)	12.52 GB	Quantized text model weights
`mmproj-devstral-small-2-f16.gguf`	F16 mmproj	0.82 GB	Vision encoder projector (24-layer SigLIP, 1024 hidden)
`README.md`	Markdown	-	Model card

Quantization Details

Property	Value
Format	NVFP4
Bits Per Weight	4.56 BPW
File Size	12.52 GB (text) + 0.82 GB (mmproj)
Tensor Count	363 (text) + 222 (mmproj)
Architecture	Mistral3 (mistral3)

Model Description

Developer: Mistral AI
Base Model: Mistral-Small-3.1-24B-Base-2503
Architecture: Dense transformer, Mistral3ForConditionalGeneration
Parameters: 24B
Context Length: 393,216 tokens (native)
Vision: 24-layer SigLIP ViT (1024 hidden), image-text-to-text
Capabilities: Coding, tool calling, agentic workflows
Languages: Multilingual
License: Apache 2.0

Usage

llama.cpp (CLI)

# Text + Image
llama-cli -m devstral-small-2-nvfp4.gguf \
  --mmproj mmproj-devstral-small-2-f16.gguf \
  --image photo.jpg \
  -p "Describe this image in detail" \
  -n 512

# Text only
llama-cli -m devstral-small-2-nvfp4.gguf \
  -p "Write a Python function to sort a list" \
  -n 512

# OpenAI-compatible server
llama-server -m devstral-small-2-nvfp4.gguf \
  --mmproj mmproj-devstral-small-2-f16.gguf \
  --port 8080

llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
    repo_id="FreedomAISVR/Devstral-Small-2-NVFP4-GGUF",
    filename="devstral-small-2-nvfp4.gguf",
    n_gpu_layers=-1,
)

response = llm.create_chat_completion([
    {"role": "user", "content": "Write a Python function to sort a list"}
])
print(response["choices"][0]["message"]["content"])

Direct download

from huggingface_hub import hf_hub_download

for filename in ["devstral-small-2-nvfp4.gguf", "mmproj-devstral-small-2-f16.gguf"]:
    hf_hub_download(
        repo_id="FreedomAISVR/Devstral-Small-2-NVFP4-GGUF",
        filename=filename,
        local_dir="./models"
    )

Quantization Pipeline

1. Download source weights
   huggingface_hub.snapshot_download("mistralai/Devstral-Small-2-24B-Instruct-2512")

2. Convert text model to F16 GGUF (dequantize FP8)
   convert_hf_to_gguf.py --outtype f16

3. Extract vision encoder
   convert_hf_to_gguf.py --mmproj --outtype f16

4. Quantize to NVFP4
   llama-quantize devstral-small-2-f16.gguf devstral-small-2-nvfp4.gguf NVFP4