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

Poor performance and pretty lobotomized

by mancub - opened Mar 18

Discussion

mancub

Mar 18

On 3x RTX 3090 it starts at 45 t/s and then drops down to 15t/s after just 1-2k tokens.

But the worst part is that the model is apparently pretty much lobotomized because of the EU regulations, according to this post: https://huggingface.co/mistralai/Mistral-Small-4-119B-2603/discussions/15#69b9c5d1f1f8dffafd58d45f

Seems like going back to some variant of Mistral 3 is going to be my next step on this journey...

noctrex

Owner Mar 18

Yeah, this model seems a little bit...weird. Having the previous small at 24b, and this at 119b is a blow to people with one card to run it. I have one card and must offload it to RAM, so it's slow from the start.
As for the intelligence it has, the new Qwen3.5 release was so high quality that all models seem inferior to it.

mancub

Mar 18

•

edited Mar 18

@noctrex

Indeed, I've been playing with Qwen3.5-27B and that model is really something else.

But not all quants are the same, and to someone who is interested in quants and who produces them I'd like to point you in the direction of QuantTrio's Qwen3.5-27B-AWQ, because of this comment https://huggingface.co/QuantTrio/Qwen3.5-27B-AWQ/discussions/2 that made me look into it further.

I do not know what QuantTrio did to their quant (not yet - need to compare all the layers I guess and try to understand what it all means LOL) but none of the other 27Bs I tried can render an analog clock correctly, on the first shot. And neither do 35B or the 122B from most of the usual suspects on here (including you). 😃

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment