Instructions to use maczzzzzz/GLM-4.7-Flash-REAP-23B-A3B-ROCmFPX-STRIX_LEAN-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use maczzzzzz/GLM-4.7-Flash-REAP-23B-A3B-ROCmFPX-STRIX_LEAN-GGUF with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="maczzzzzz/GLM-4.7-Flash-REAP-23B-A3B-ROCmFPX-STRIX_LEAN-GGUF", filename="GLM-4.7-Flash-REAP-23B-A3B-ROCmFPX-STRIX_LEAN.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use maczzzzzz/GLM-4.7-Flash-REAP-23B-A3B-ROCmFPX-STRIX_LEAN-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 maczzzzzz/GLM-4.7-Flash-REAP-23B-A3B-ROCmFPX-STRIX_LEAN-GGUF # Run inference directly in the terminal: llama cli -hf maczzzzzz/GLM-4.7-Flash-REAP-23B-A3B-ROCmFPX-STRIX_LEAN-GGUF
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf maczzzzzz/GLM-4.7-Flash-REAP-23B-A3B-ROCmFPX-STRIX_LEAN-GGUF # Run inference directly in the terminal: llama cli -hf maczzzzzz/GLM-4.7-Flash-REAP-23B-A3B-ROCmFPX-STRIX_LEAN-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 maczzzzzz/GLM-4.7-Flash-REAP-23B-A3B-ROCmFPX-STRIX_LEAN-GGUF # Run inference directly in the terminal: ./llama-cli -hf maczzzzzz/GLM-4.7-Flash-REAP-23B-A3B-ROCmFPX-STRIX_LEAN-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 maczzzzzz/GLM-4.7-Flash-REAP-23B-A3B-ROCmFPX-STRIX_LEAN-GGUF # Run inference directly in the terminal: ./build/bin/llama-cli -hf maczzzzzz/GLM-4.7-Flash-REAP-23B-A3B-ROCmFPX-STRIX_LEAN-GGUF
Use Docker
docker model run hf.co/maczzzzzz/GLM-4.7-Flash-REAP-23B-A3B-ROCmFPX-STRIX_LEAN-GGUF
- LM Studio
- Jan
- Ollama
How to use maczzzzzz/GLM-4.7-Flash-REAP-23B-A3B-ROCmFPX-STRIX_LEAN-GGUF with Ollama:
ollama run hf.co/maczzzzzz/GLM-4.7-Flash-REAP-23B-A3B-ROCmFPX-STRIX_LEAN-GGUF
- Unsloth Studio
How to use maczzzzzz/GLM-4.7-Flash-REAP-23B-A3B-ROCmFPX-STRIX_LEAN-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 maczzzzzz/GLM-4.7-Flash-REAP-23B-A3B-ROCmFPX-STRIX_LEAN-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 maczzzzzz/GLM-4.7-Flash-REAP-23B-A3B-ROCmFPX-STRIX_LEAN-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for maczzzzzz/GLM-4.7-Flash-REAP-23B-A3B-ROCmFPX-STRIX_LEAN-GGUF to start chatting
- Pi
How to use maczzzzzz/GLM-4.7-Flash-REAP-23B-A3B-ROCmFPX-STRIX_LEAN-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf maczzzzzz/GLM-4.7-Flash-REAP-23B-A3B-ROCmFPX-STRIX_LEAN-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": "maczzzzzz/GLM-4.7-Flash-REAP-23B-A3B-ROCmFPX-STRIX_LEAN-GGUF" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use maczzzzzz/GLM-4.7-Flash-REAP-23B-A3B-ROCmFPX-STRIX_LEAN-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 maczzzzzz/GLM-4.7-Flash-REAP-23B-A3B-ROCmFPX-STRIX_LEAN-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 maczzzzzz/GLM-4.7-Flash-REAP-23B-A3B-ROCmFPX-STRIX_LEAN-GGUF
Run Hermes
hermes
- Atomic Chat new
- OpenClaw new
How to use maczzzzzz/GLM-4.7-Flash-REAP-23B-A3B-ROCmFPX-STRIX_LEAN-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf maczzzzzz/GLM-4.7-Flash-REAP-23B-A3B-ROCmFPX-STRIX_LEAN-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 "maczzzzzz/GLM-4.7-Flash-REAP-23B-A3B-ROCmFPX-STRIX_LEAN-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 maczzzzzz/GLM-4.7-Flash-REAP-23B-A3B-ROCmFPX-STRIX_LEAN-GGUF with Docker Model Runner:
docker model run hf.co/maczzzzzz/GLM-4.7-Flash-REAP-23B-A3B-ROCmFPX-STRIX_LEAN-GGUF
- Lemonade
How to use maczzzzzz/GLM-4.7-Flash-REAP-23B-A3B-ROCmFPX-STRIX_LEAN-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull maczzzzzz/GLM-4.7-Flash-REAP-23B-A3B-ROCmFPX-STRIX_LEAN-GGUF
Run and chat with the model
lemonade run user.GLM-4.7-Flash-REAP-23B-A3B-ROCmFPX-STRIX_LEAN-GGUF-{{QUANT_TAG}}List all available models
lemonade list
| { | |
| "label": "glm-reap-23b-strix_lean", | |
| "endpoint": "http://node-b:18082", | |
| "timestamp": "2026-06-27T18:12:30.765358+00:00", | |
| "scenarios": [ | |
| { | |
| "scenario": "single", | |
| "description": "Single tool call \u2014 model must call get_weather for Tokyo", | |
| "status": "PASS", | |
| "tool_match": true, | |
| "tools_called": [ | |
| "get_weather" | |
| ], | |
| "expected_tool": "get_weather", | |
| "all_args_valid": true, | |
| "final_answer_correct": true, | |
| "final_answer_preview": "The current weather in Tokyo is:\n\n- **Temperature**: 22\u00b0C (72\u00b0F)\n- **Condition**: Partly cloudy\n- **Humidity**: 65%", | |
| "turns_used": 2, | |
| "max_turns": 3, | |
| "efficiency": "OPTIMAL", | |
| "total_time_s": 1.59, | |
| "avg_tps": 38.5, | |
| "turns": [ | |
| { | |
| "turn": 1, | |
| "elapsed_s": 0.92, | |
| "tps": 25.1, | |
| "finish_reason": "tool_calls", | |
| "content_preview": "I'll check the current weather in Tokyo for you.", | |
| "tool_calls": [ | |
| { | |
| "name": "get_weather", | |
| "args": { | |
| "location": "Tokyo" | |
| }, | |
| "args_valid": true | |
| } | |
| ] | |
| }, | |
| { | |
| "turn": 2, | |
| "elapsed_s": 0.67, | |
| "tps": 51.9, | |
| "finish_reason": "stop", | |
| "content_preview": "The current weather in Tokyo is:\n\n- **Temperature**: 22\u00b0C (72\u00b0F)\n- **Condition**: Partly cloudy\n- **Humidity**: 65%", | |
| "tool_calls": [], | |
| "final": true | |
| } | |
| ] | |
| }, | |
| { | |
| "scenario": "chained", | |
| "description": "Chained tool calls \u2014 calculate then use result", | |
| "status": "PASS", | |
| "tool_match": true, | |
| "tools_called": [ | |
| "calculate" | |
| ], | |
| "expected_tool": "calculate", | |
| "all_args_valid": true, | |
| "final_answer_correct": true, | |
| "final_answer_preview": "15 * 37 = 555", | |
| "turns_used": 2, | |
| "max_turns": 3, | |
| "efficiency": "OPTIMAL", | |
| "total_time_s": 0.61, | |
| "avg_tps": 35.8, | |
| "turns": [ | |
| { | |
| "turn": 1, | |
| "elapsed_s": 0.31, | |
| "tps": 42.2, | |
| "finish_reason": "tool_calls", | |
| "content_preview": "", | |
| "tool_calls": [ | |
| { | |
| "name": "calculate", | |
| "args": { | |
| "expression": "15 * 37" | |
| }, | |
| "args_valid": true | |
| } | |
| ] | |
| }, | |
| { | |
| "turn": 2, | |
| "elapsed_s": 0.31, | |
| "tps": 29.3, | |
| "finish_reason": "stop", | |
| "content_preview": "15 * 37 = 555", | |
| "tool_calls": [], | |
| "final": true | |
| } | |
| ] | |
| }, | |
| { | |
| "scenario": "multi_step", | |
| "description": "Multi-step \u2014 compare weather in two cities", | |
| "status": "PASS", | |
| "tool_match": true, | |
| "tools_called": [ | |
| "get_weather", | |
| "get_weather" | |
| ], | |
| "expected_tool": [ | |
| "get_weather", | |
| "get_weather" | |
| ], | |
| "all_args_valid": true, | |
| "final_answer_correct": true, | |
| "final_answer_preview": "Based on the current weather data:\n\n**Tokyo:** 22\u00b0C (partly cloudy, 65% humidity)\n**London:** 15\u00b0C (rainy, 80% humidity)\n\n**Tokyo is warmer** - it's 7 degrees hotter than London (22\u00b0C vs 15\u00b0C).", | |
| "turns_used": 2, | |
| "max_turns": 5, | |
| "efficiency": "OPTIMAL", | |
| "total_time_s": 1.94, | |
| "avg_tps": 50.8, | |
| "turns": [ | |
| { | |
| "turn": 1, | |
| "elapsed_s": 0.72, | |
| "tps": 50.2, | |
| "finish_reason": "tool_calls", | |
| "content_preview": "I'll get the current weather for both cities and then compare them.", | |
| "tool_calls": [ | |
| { | |
| "name": "get_weather", | |
| "args": { | |
| "location": "Tokyo" | |
| }, | |
| "args_valid": true | |
| }, | |
| { | |
| "name": "get_weather", | |
| "args": { | |
| "location": "London" | |
| }, | |
| "args_valid": true | |
| } | |
| ] | |
| }, | |
| { | |
| "turn": 2, | |
| "elapsed_s": 1.23, | |
| "tps": 51.3, | |
| "finish_reason": "stop", | |
| "content_preview": "Based on the current weather data:\n\n**Tokyo:** 22\u00b0C (partly cloudy, 65% humidity)\n**London:** 15\u00b0C (rainy, 80% humidity)\n\n**Tokyo is warmer** - it's 7 degrees hotter than London (22\u00b0C vs 15\u00b0C).", | |
| "tool_calls": [], | |
| "final": true | |
| } | |
| ] | |
| }, | |
| { | |
| "scenario": "search", | |
| "description": "Search + extract \u2014 find info and report it", | |
| "status": "PASS", | |
| "tool_match": true, | |
| "tools_called": [ | |
| "search_web" | |
| ], | |
| "expected_tool": "search_web", | |
| "all_args_valid": true, | |
| "final_answer_correct": true, | |
| "final_answer_preview": "According to the search results, the Eiffel Tower is **330 meters tall**.", | |
| "turns_used": 2, | |
| "max_turns": 3, | |
| "efficiency": "OPTIMAL", | |
| "total_time_s": 1.02, | |
| "avg_tps": 46.8, | |
| "turns": [ | |
| { | |
| "turn": 1, | |
| "elapsed_s": 0.61, | |
| "tps": 47.2, | |
| "finish_reason": "tool_calls", | |
| "content_preview": "I'll search for information about the Eiffel Tower's height.", | |
| "tool_calls": [ | |
| { | |
| "name": "search_web", | |
| "args": { | |
| "query": "Eiffel Tower height" | |
| }, | |
| "args_valid": true | |
| } | |
| ] | |
| }, | |
| { | |
| "turn": 2, | |
| "elapsed_s": 0.41, | |
| "tps": 46.4, | |
| "finish_reason": "stop", | |
| "content_preview": "According to the search results, the Eiffel Tower is **330 meters tall**.", | |
| "tool_calls": [], | |
| "final": true | |
| } | |
| ] | |
| }, | |
| { | |
| "scenario": "error_recovery", | |
| "description": "Error recovery \u2014 file doesn't exist, model should report it", | |
| "status": "PASS", | |
| "tool_match": true, | |
| "tools_called": [ | |
| "read_file" | |
| ], | |
| "expected_tool": "read_file", | |
| "all_args_valid": true, | |
| "final_answer_correct": true, | |
| "final_answer_preview": "The file `/nonexistent/path.txt` does not exist. The system returned an error indicating that the file wasn't found.", | |
| "turns_used": 2, | |
| "max_turns": 3, | |
| "efficiency": "OPTIMAL", | |
| "total_time_s": 1.02, | |
| "avg_tps": 48.9, | |
| "turns": [ | |
| { | |
| "turn": 1, | |
| "elapsed_s": 0.51, | |
| "tps": 47.0, | |
| "finish_reason": "tool_calls", | |
| "content_preview": "I'll attempt to read the file for you.", | |
| "tool_calls": [ | |
| { | |
| "name": "read_file", | |
| "args": { | |
| "path": "/nonexistent/path.txt" | |
| }, | |
| "args_valid": true | |
| } | |
| ] | |
| }, | |
| { | |
| "turn": 2, | |
| "elapsed_s": 0.51, | |
| "tps": 50.8, | |
| "finish_reason": "stop", | |
| "content_preview": "The file `/nonexistent/path.txt` does not exist. The system returned an error indicating that the file wasn't found.", | |
| "tool_calls": [], | |
| "final": true | |
| } | |
| ] | |
| } | |
| ], | |
| "overall_status": "PASS", | |
| "pass_count": "5/5", | |
| "framework": "hermes_loop_eval.py v1.0" | |
| } |