Instructions to use noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-GGUF",
	filename="Mistral-Small-4-119B-2603-MXFP4_MOE_BF16-00001-of-00004.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-GGUF:MXFP4_MOE_BF
# Run inference directly in the terminal:
llama-cli -hf noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-GGUF:MXFP4_MOE_BF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-GGUF:MXFP4_MOE_BF
# Run inference directly in the terminal:
llama-cli -hf noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-GGUF:MXFP4_MOE_BF

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 noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-GGUF:MXFP4_MOE_BF
# Run inference directly in the terminal:
./llama-cli -hf noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-GGUF:MXFP4_MOE_BF

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 noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-GGUF:MXFP4_MOE_BF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-GGUF:MXFP4_MOE_BF

Use Docker

docker model run hf.co/noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-GGUF:MXFP4_MOE_BF

LM Studio
Jan

vLLM

How to use noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-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": "noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-GGUF:MXFP4_MOE_BF

Ollama

How to use noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-GGUF with Ollama:

ollama run hf.co/noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-GGUF:MXFP4_MOE_BF

Unsloth Studio

How to use noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-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 noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-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 noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-GGUF to start chatting

How to use noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-GGUF:MXFP4_MOE_BF

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": "noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-GGUF:MXFP4_MOE_BF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-GGUF:MXFP4_MOE_BF

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 noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-GGUF:MXFP4_MOE_BF

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-GGUF with Docker Model Runner:
```
docker model run hf.co/noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-GGUF:MXFP4_MOE_BF
```

Lemonade

How to use noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-GGUF:MXFP4_MOE_BF

Run and chat with the model

lemonade run user.Mistral-Small-4-119B-2603-MXFP4_MOE-GGUF-MXFP4_MOE_BF

List all available models

lemonade list

This is a MXFP4_MOE quantization of the model Mistral-Small-4-119B-2603

Download the latest llama.cpp to use it.
For the mmproj file, the F32 version is recommended for best results. F32 > BF16 > F16

The mainline standard is to use MXFP4 for the MoE tensors, and Q8 for the rest.
So I created a new variant, where the other tensors are BF16 instead of Q8.
On some architectures BF16 will be slower, but its the highest quality, essentialy its the original tensors from the model copied over unquantized.
This model here has been quantized like this.

Downloads last month: 103

GGUF

Model size

119B params

Architecture

mistral4

Hardware compatibility

4-bit

Model tree for noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-GGUF

Base model

mistralai/Mistral-Small-4-119B-2603

Quantized

(31)

this model