Instructions to use noctrex/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill 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-Claude-Opus-4.5-High-Reasoning-Distill 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-Claude-Opus-4.5-High-Reasoning-Distill:MXFP4_MOE
# Run inference directly in the terminal:
llama cli -hf noctrex/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill: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-Claude-Opus-4.5-High-Reasoning-Distill:MXFP4_MOE
# Run inference directly in the terminal:
llama cli -hf noctrex/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill: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-Claude-Opus-4.5-High-Reasoning-Distill:MXFP4_MOE
# Run inference directly in the terminal:
./llama-cli -hf noctrex/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill: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-Claude-Opus-4.5-High-Reasoning-Distill:MXFP4_MOE
# Run inference directly in the terminal:
./build/bin/llama-cli -hf noctrex/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill:MXFP4_MOE

Use Docker

docker model run hf.co/noctrex/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill:MXFP4_MOE

LM Studio
Jan

vLLM

How to use noctrex/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill 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-Claude-Opus-4.5-High-Reasoning-Distill"
# 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-Claude-Opus-4.5-High-Reasoning-Distill",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/noctrex/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill:MXFP4_MOE

Ollama
How to use noctrex/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill with Ollama:
```
ollama run hf.co/noctrex/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill:MXFP4_MOE
```
Unsloth Desktop

How to use noctrex/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill 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-Claude-Opus-4.5-High-Reasoning-Distill:MXFP4_MOE

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/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-Claude-Opus-4.5-High-Reasoning-Distill:MXFP4_MOE"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use noctrex/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill with Docker Model Runner:
```
docker model run hf.co/noctrex/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill:MXFP4_MOE
```

Lemonade

How to use noctrex/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull noctrex/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill:MXFP4_MOE

Run and chat with the model

lemonade run user.GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill-MXFP4_MOE

List all available models

lemonade list

Hermes Agent

How to use noctrex/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill 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-Claude-Opus-4.5-High-Reasoning-Distill: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-Claude-Opus-4.5-High-Reasoning-Distill:MXFP4_MOE

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use noctrex/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill 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-Claude-Opus-4.5-High-Reasoning-Distill: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-Claude-Opus-4.5-High-Reasoning-Distill: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"

These are MXFP4_MOE quantizations of the model GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill.

I have created a normal one, and also an importance-aware MXFP4_MOE quantization that dynamically allocates precision based on tensor importance scores from an imatrix I created with code_tiny.
This is a coding optimized quantization and is slightly larger than the mainline MXFP4_MOE, and the way it works is that it keeps a better quantization depending on the importance of each tensor.

BF16 (16-bit) for highly important tensors (>75% importance)
Q8_0 (8-bit) for moderately important tensors (>60% importance)
MXFP4 (4-bit) for less important tensors (<50% importance)

As I've mentioned it is experimental, and still not have done any benchmark on it, to see if it's any better than mainline, but you are freely to try it out and report back!

Downloads last month: 137

GGUF

Model size

30B params

Architecture

deepseek2

Hardware compatibility

4-bit

View +1 variant

Model tree for noctrex/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill

Base model

zai-org/GLM-4.7-Flash

Finetuned

unsloth/GLM-4.7-Flash

Finetuned

TeichAI/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill

Quantized

(14)

this model