Instructions to use xrist0bg/GLM-4.7-Flash-MXFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use xrist0bg/GLM-4.7-Flash-MXFP4 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 xrist0bg/GLM-4.7-Flash-MXFP4:MXFP4
# Run inference directly in the terminal:
llama cli -hf xrist0bg/GLM-4.7-Flash-MXFP4:MXFP4

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf xrist0bg/GLM-4.7-Flash-MXFP4:MXFP4
# Run inference directly in the terminal:
llama cli -hf xrist0bg/GLM-4.7-Flash-MXFP4:MXFP4

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 xrist0bg/GLM-4.7-Flash-MXFP4:MXFP4
# Run inference directly in the terminal:
./llama-cli -hf xrist0bg/GLM-4.7-Flash-MXFP4:MXFP4

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 xrist0bg/GLM-4.7-Flash-MXFP4:MXFP4
# Run inference directly in the terminal:
./build/bin/llama-cli -hf xrist0bg/GLM-4.7-Flash-MXFP4:MXFP4

Use Docker

docker model run hf.co/xrist0bg/GLM-4.7-Flash-MXFP4:MXFP4

LM Studio
Jan
Ollama
How to use xrist0bg/GLM-4.7-Flash-MXFP4 with Ollama:
```
ollama run hf.co/xrist0bg/GLM-4.7-Flash-MXFP4:MXFP4
```
Unsloth Desktop

How to use xrist0bg/GLM-4.7-Flash-MXFP4 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf xrist0bg/GLM-4.7-Flash-MXFP4:MXFP4

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": "xrist0bg/GLM-4.7-Flash-MXFP4:MXFP4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use xrist0bg/GLM-4.7-Flash-MXFP4 with Docker Model Runner:
```
docker model run hf.co/xrist0bg/GLM-4.7-Flash-MXFP4:MXFP4
```

Lemonade

How to use xrist0bg/GLM-4.7-Flash-MXFP4 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull xrist0bg/GLM-4.7-Flash-MXFP4:MXFP4

Run and chat with the model

lemonade run user.GLM-4.7-Flash-MXFP4-MXFP4

List all available models

lemonade list

Hermes Agent

How to use xrist0bg/GLM-4.7-Flash-MXFP4 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf xrist0bg/GLM-4.7-Flash-MXFP4:MXFP4

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 xrist0bg/GLM-4.7-Flash-MXFP4:MXFP4

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use xrist0bg/GLM-4.7-Flash-MXFP4 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf xrist0bg/GLM-4.7-Flash-MXFP4:MXFP4

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 "xrist0bg/GLM-4.7-Flash-MXFP4:MXFP4" \
  --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"

llama.cpp version: b7802

Quantization command:

./build/bin/llama-quantize \
  --token-embedding-type f16 \
  --output-tensor-type f16 \
  --tensor-type ".*attn.*=F16" \
  --tensor-type ".*norm.*=F32" \
  --tensor-type ".*bias=F16" \
  --tensor-type ".*shexp.*=F16" \
  GLM-4.7-Flash-F16.gguf \
  GLM-4.7-Flash-MXFP4.gguf \
  MXFP4_MOE

i changed the moe experts (other than the shared expert) to mxfp4 and the dense layer to q8 and keep everything else the same as original for best quality

i can load only around 45k context on 3090 with this config tho

Downloads last month: 9

GGUF

Model size

30B params

Architecture

deepseek2

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for xrist0bg/GLM-4.7-Flash-MXFP4

Base model

zai-org/GLM-4.7-Flash

Quantized

(97)

this model