Instructions to use noctrex/Qwen3-Coder-Next-MXFP4_MOE-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 noctrex/Qwen3-Coder-Next-MXFP4_MOE-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 noctrex/Qwen3-Coder-Next-MXFP4_MOE-GGUF:MXFP4_MOE_BF
# Run inference directly in the terminal:
llama cli -hf noctrex/Qwen3-Coder-Next-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 serve -hf noctrex/Qwen3-Coder-Next-MXFP4_MOE-GGUF:MXFP4_MOE_BF
# Run inference directly in the terminal:
llama cli -hf noctrex/Qwen3-Coder-Next-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/Qwen3-Coder-Next-MXFP4_MOE-GGUF:MXFP4_MOE_BF
# Run inference directly in the terminal:
./llama-cli -hf noctrex/Qwen3-Coder-Next-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/Qwen3-Coder-Next-MXFP4_MOE-GGUF:MXFP4_MOE_BF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf noctrex/Qwen3-Coder-Next-MXFP4_MOE-GGUF:MXFP4_MOE_BF

Use Docker

docker model run hf.co/noctrex/Qwen3-Coder-Next-MXFP4_MOE-GGUF:MXFP4_MOE_BF

LM Studio
Jan

vLLM

How to use noctrex/Qwen3-Coder-Next-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/Qwen3-Coder-Next-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/Qwen3-Coder-Next-MXFP4_MOE-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/noctrex/Qwen3-Coder-Next-MXFP4_MOE-GGUF:MXFP4_MOE_BF

Ollama

How to use noctrex/Qwen3-Coder-Next-MXFP4_MOE-GGUF with Ollama:

ollama run hf.co/noctrex/Qwen3-Coder-Next-MXFP4_MOE-GGUF:MXFP4_MOE_BF

Unsloth Studio

How to use noctrex/Qwen3-Coder-Next-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/Qwen3-Coder-Next-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/Qwen3-Coder-Next-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/Qwen3-Coder-Next-MXFP4_MOE-GGUF to start chatting

How to use noctrex/Qwen3-Coder-Next-MXFP4_MOE-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf noctrex/Qwen3-Coder-Next-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/Qwen3-Coder-Next-MXFP4_MOE-GGUF:MXFP4_MOE_BF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use noctrex/Qwen3-Coder-Next-MXFP4_MOE-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf noctrex/Qwen3-Coder-Next-MXFP4_MOE-GGUF:MXFP4_MOE_BF

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 "noctrex/Qwen3-Coder-Next-MXFP4_MOE-GGUF:MXFP4_MOE_BF" \
  --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 noctrex/Qwen3-Coder-Next-MXFP4_MOE-GGUF with Docker Model Runner:
```
docker model run hf.co/noctrex/Qwen3-Coder-Next-MXFP4_MOE-GGUF:MXFP4_MOE_BF
```

Lemonade

How to use noctrex/Qwen3-Coder-Next-MXFP4_MOE-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull noctrex/Qwen3-Coder-Next-MXFP4_MOE-GGUF:MXFP4_MOE_BF

Run and chat with the model

lemonade run user.Qwen3-Coder-Next-MXFP4_MOE-GGUF-MXFP4_MOE_BF

List all available models

lemonade list

Hermes Agent

How to use noctrex/Qwen3-Coder-Next-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 serve -hf noctrex/Qwen3-Coder-Next-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/Qwen3-Coder-Next-MXFP4_MOE-GGUF:MXFP4_MOE_BF

Run Hermes

hermes

Atomic Chat

This is a MXFP4_MOE quantization of the model Qwen3-Coder-Next

The suggested parameters from the official docs are:

temperature=1.0
top_p=0.95
top_k=40

As of 2026-02-17 I have updated the model to a MXFP4 quant of higher quality.

The mainline standard is to use MXFP4 for the MoE tensors, and Q8 for the rest.
So I created 2 new variants, where the other tensors are either BF16 or FP16 instead of Q8. The order of preference is BF16, then F16. On some architectures BF16 will be slower, but its the highest quality, essentialy its the original tensors from the model copied over unquantized.

Downloads last month: 455

GGUF

Model size

80B params

Architecture

qwen3next

Hardware compatibility

4-bit

Model tree for noctrex/Qwen3-Coder-Next-MXFP4_MOE-GGUF

Base model

Qwen/Qwen3-Coder-Next

Quantized

(113)

this model