Instructions to use noctrex/GLM-4.7-Flash-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/GLM-4.7-Flash-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/GLM-4.7-Flash-MXFP4_MOE-GGUF:MXFP4_MOE
# Run inference directly in the terminal:
llama cli -hf noctrex/GLM-4.7-Flash-MXFP4_MOE-GGUF:MXFP4_MOE

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf noctrex/GLM-4.7-Flash-MXFP4_MOE-GGUF:MXFP4_MOE
# Run inference directly in the terminal:
llama cli -hf noctrex/GLM-4.7-Flash-MXFP4_MOE-GGUF:MXFP4_MOE

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/GLM-4.7-Flash-MXFP4_MOE-GGUF:MXFP4_MOE
# Run inference directly in the terminal:
./llama-cli -hf noctrex/GLM-4.7-Flash-MXFP4_MOE-GGUF:MXFP4_MOE

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/GLM-4.7-Flash-MXFP4_MOE-GGUF:MXFP4_MOE
# Run inference directly in the terminal:
./build/bin/llama-cli -hf noctrex/GLM-4.7-Flash-MXFP4_MOE-GGUF:MXFP4_MOE

Use Docker

docker model run hf.co/noctrex/GLM-4.7-Flash-MXFP4_MOE-GGUF:MXFP4_MOE

LM Studio
Jan

vLLM

How to use noctrex/GLM-4.7-Flash-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/GLM-4.7-Flash-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/GLM-4.7-Flash-MXFP4_MOE-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/noctrex/GLM-4.7-Flash-MXFP4_MOE-GGUF:MXFP4_MOE

Ollama
How to use noctrex/GLM-4.7-Flash-MXFP4_MOE-GGUF with Ollama:
```
ollama run hf.co/noctrex/GLM-4.7-Flash-MXFP4_MOE-GGUF:MXFP4_MOE
```

Unsloth Studio

How to use noctrex/GLM-4.7-Flash-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/GLM-4.7-Flash-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/GLM-4.7-Flash-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/GLM-4.7-Flash-MXFP4_MOE-GGUF to start chatting

How to use noctrex/GLM-4.7-Flash-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/GLM-4.7-Flash-MXFP4_MOE-GGUF:MXFP4_MOE

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/GLM-4.7-Flash-MXFP4_MOE-GGUF:MXFP4_MOE"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use noctrex/GLM-4.7-Flash-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/GLM-4.7-Flash-MXFP4_MOE-GGUF:MXFP4_MOE

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/GLM-4.7-Flash-MXFP4_MOE-GGUF:MXFP4_MOE" \
  --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/GLM-4.7-Flash-MXFP4_MOE-GGUF with Docker Model Runner:
```
docker model run hf.co/noctrex/GLM-4.7-Flash-MXFP4_MOE-GGUF:MXFP4_MOE
```

Lemonade

How to use noctrex/GLM-4.7-Flash-MXFP4_MOE-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull noctrex/GLM-4.7-Flash-MXFP4_MOE-GGUF:MXFP4_MOE

Run and chat with the model

lemonade run user.GLM-4.7-Flash-MXFP4_MOE-GGUF-MXFP4_MOE

List all available models

lemonade list

Hermes Agent

How to use noctrex/GLM-4.7-Flash-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/GLM-4.7-Flash-MXFP4_MOE-GGUF:MXFP4_MOE

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/GLM-4.7-Flash-MXFP4_MOE-GGUF:MXFP4_MOE

Run Hermes

hermes

Atomic Chat

Is this static quantization without using imatrix?

by MrPippin - opened Feb 4

Discussion

MrPippin

Feb 4

First of all, thank you for your work.

My question is this: did you use any approaches for weighted quantization? Like importance matrix, calibration datasets, and all that? Or is it completely static quantization?

I have to work with texts in three languages: English, Russian and Chinese, and I noticed that your version subjectively makes fewer mistakes when generating answers in a non-English language than the UD-Q4_K_XL quants from Unsloth.

Could this behavior be related to static quantization? The calibration datasets used in dynamic quantization seem to be all in English. Could this somehow affect the neural network's performance with other languages? Perhaps I'm misunderstanding something about this process. Please help me figure it out.

noctrex

Owner Feb 4

Actually the MXFP4_MOE quantization does not make a use of an imatrix. It's very simple in structure: quantize all MoE experts to FP4, and everything else to Q8. Very simple.

MrPippin

Feb 4

Do you think that using the importance matrix in dynamic quantization might further worsen the model's ability to respond to other languages or domains of knowledge that were not covered by the calibration dataset, compared to static quantization where, as I understand it, the weights are quantized more uniformly?

noctrex

Owner Feb 4

I don't really know. I've created some experimental ones, like this one: https://huggingface.co/noctrex/GLM-4.7-Flash-i1-MXFP4_MOE_XL-exp-GGUF
But I haven't have the time to proper benchmark it yet to see if it's really any better.

MrPippin

Feb 4

Anyway, thank you very much for your work!

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