Instructions to use ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-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 ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-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 ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-GGUF
# Run inference directly in the terminal:
llama cli -hf ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-GGUF
# Run inference directly in the terminal:
llama cli -hf ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-GGUF

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 ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-GGUF
# Run inference directly in the terminal:
./llama-cli -hf ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-GGUF

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 ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-GGUF

Use Docker

docker model run hf.co/ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-GGUF

LM Studio
Jan

vLLM

How to use ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-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": "ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-GGUF

Ollama
How to use ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-GGUF with Ollama:
```
ollama run hf.co/ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-GGUF
```

Unsloth Studio

How to use ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-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 ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-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 ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-GGUF to start chatting

How to use ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-GGUF

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": "ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-GGUF

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 "ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-GGUF" \
  --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 ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-GGUF with Docker Model Runner:
```
docker model run hf.co/ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-GGUF
```

Lemonade

How to use ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-GGUF

Run and chat with the model

lemonade run user.GLM-4.7-Flash-Uncensored-750-v1-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-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 ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-GGUF

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 ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-GGUF

Run Hermes

hermes

Atomic Chat

4bpw feedback

by TheodoreH - opened 7 days ago

Discussion

TheodoreH

7 days ago

Hi. Since there is no posibilities to run models bigger than 15 gb - stuck with that one, and having issues. It loops quite frequently, but for 4bpw it should be much better(using qwen 35b with 3.5 bits and it had never looped at all, but GLM loops almost every third answer and if message is going long(none code one) it loops too). tried different settings, but lower temps or pens - fix(somewhat) hallucinating and loosing grip of logic in text, but it is not perfect, or not at least fine, bearable for now. it is shame, because GLM seems to write in very different manner than Gemma or Qwen, and it is the only reason it makes sense to try it more. Still thanks for upload, because there are none really similar quants for this model. Usually use Apex quants or Cerebellum, but there are none fore unfiltered GLM that can be used normally. All availible (less than 15gb) quants or IQ3M - or 3 KM - is far worse and dont work normally at all. From DavidAU it runs much slower for some reason(but model is same).

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