GLM 4.7 GGUF references
Collection
Preserved GLM4.7 text/MTP GGUF references with matched checks. Made by Xylolabs. Not affiliated with or endorsed by Tenstorrent. โข 1 item โข Updated
How to use Xylolabs/GLM-4.7-Flash-GGUF with llama.cpp:
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf Xylolabs/GLM-4.7-Flash-GGUF:IQ4_XS # Run inference directly in the terminal: llama cli -hf Xylolabs/GLM-4.7-Flash-GGUF:IQ4_XS
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Xylolabs/GLM-4.7-Flash-GGUF:IQ4_XS # Run inference directly in the terminal: llama cli -hf Xylolabs/GLM-4.7-Flash-GGUF:IQ4_XS
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf Xylolabs/GLM-4.7-Flash-GGUF:IQ4_XS # Run inference directly in the terminal: ./build/bin/llama cli -hf Xylolabs/GLM-4.7-Flash-GGUF:IQ4_XS
docker model run hf.co/Xylolabs/GLM-4.7-Flash-GGUF:IQ4_XS
How to use Xylolabs/GLM-4.7-Flash-GGUF with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Xylolabs/GLM-4.7-Flash-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": "Xylolabs/GLM-4.7-Flash-GGUF",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}'docker model run hf.co/Xylolabs/GLM-4.7-Flash-GGUF:IQ4_XS
How to use Xylolabs/GLM-4.7-Flash-GGUF with Ollama:
ollama run hf.co/Xylolabs/GLM-4.7-Flash-GGUF:IQ4_XS
How to use Xylolabs/GLM-4.7-Flash-GGUF with Pi:
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Xylolabs/GLM-4.7-Flash-GGUF:IQ4_XS
# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
"providers": {
"llama-cpp": {
"baseUrl": "http://localhost:9931/v1",
"api": "openai-completions",
"apiKey": "none",
"models": [
{
"id": "Xylolabs/GLM-4.7-Flash-GGUF:IQ4_XS"
}
]
}
}
}# Start Pi in your project directory: pi
How to use Xylolabs/GLM-4.7-Flash-GGUF with Docker Model Runner:
docker model run hf.co/Xylolabs/GLM-4.7-Flash-GGUF:IQ4_XS
How to use Xylolabs/GLM-4.7-Flash-GGUF with Lemonade:
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Xylolabs/GLM-4.7-Flash-GGUF:IQ4_XS
lemonade run user.GLM-4.7-Flash-GGUF-IQ4_XS
lemonade list
How to use Xylolabs/GLM-4.7-Flash-GGUF with Hermes Agent:
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Xylolabs/GLM-4.7-Flash-GGUF:IQ4_XS
# 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://127.0.0.1:9931/v1 hermes config set model.default Xylolabs/GLM-4.7-Flash-GGUF:IQ4_XS
hermes
How to use Xylolabs/GLM-4.7-Flash-GGUF with OpenClaw:
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Xylolabs/GLM-4.7-Flash-GGUF:IQ4_XS
# 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://127.0.0.1:9931/v1 \ --custom-model-id "Xylolabs/GLM-4.7-Flash-GGUF:IQ4_XS" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
openclaw agent --local --agent main --message "Hello from Hugging Face"
GGUF quants of zai-org/GLM-4.7-Flash for llama.cpp, on CUDA, Metal or CPU.
GLM-4.7-Flash-<QUANT>.gguf is one file per quant.| Quant | Size | Mean KL vs BF16 | Same top-1 vs BF16 |
|---|---|---|---|
| IQ4_XS | 16.88 GB | 0.0868 | 87.80% |
| IQ4_XS-imat | 16.71 GB | 0.0845 | 88.34% |
How we measured:
Use llama.cpp commit cd959bae99ff4bed22bef2604f45241c09bbb8c8 or later.
git clone https://github.com/ggml-org/llama.cpp && cd llama.cpp
git checkout cd959bae99ff4bed22bef2604f45241c09bbb8c8
cmake -B build -DCMAKE_BUILD_TYPE=Release # add -DGGML_CUDA=ON for NVIDIA GPUs
cmake --build build -j --target llama-cli llama-server
./build/bin/llama-cli -m GLM-4.7-Flash-IQ4_XS.gguf --jinja -c 8192 -ngl 99
llama-server takes the same flags.
convert_hf_to_gguf.py.llama-quantize.-imat files use an importance matrix.LICENSE.NOTICE names the source model and its copyright holder.Cite the original GLM-4.7-Flash model card and its linked GLM technical report.
4-bit
Base model
zai-org/GLM-4.7-Flash