Instructions to use iRunStudio/Meltdown_GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use iRunStudio/Meltdown_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 iRunStudio/Meltdown_GGUF # Run inference directly in the terminal: llama cli -hf iRunStudio/Meltdown_GGUF
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf iRunStudio/Meltdown_GGUF # Run inference directly in the terminal: llama cli -hf iRunStudio/Meltdown_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 iRunStudio/Meltdown_GGUF # Run inference directly in the terminal: ./llama-cli -hf iRunStudio/Meltdown_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 iRunStudio/Meltdown_GGUF # Run inference directly in the terminal: ./build/bin/llama-cli -hf iRunStudio/Meltdown_GGUF
Use Docker
docker model run hf.co/iRunStudio/Meltdown_GGUF
- LM Studio
- Jan
- vLLM
How to use iRunStudio/Meltdown_GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "iRunStudio/Meltdown_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": "iRunStudio/Meltdown_GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/iRunStudio/Meltdown_GGUF
- Ollama
How to use iRunStudio/Meltdown_GGUF with Ollama:
ollama run hf.co/iRunStudio/Meltdown_GGUF
- Unsloth Studio
How to use iRunStudio/Meltdown_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 iRunStudio/Meltdown_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 iRunStudio/Meltdown_GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for iRunStudio/Meltdown_GGUF to start chatting
- Pi
How to use iRunStudio/Meltdown_GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf iRunStudio/Meltdown_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": "iRunStudio/Meltdown_GGUF" } ] } } }Run Pi
# Start Pi in your project directory: pi
- OpenClaw new
How to use iRunStudio/Meltdown_GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf iRunStudio/Meltdown_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 "iRunStudio/Meltdown_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 iRunStudio/Meltdown_GGUF with Docker Model Runner:
docker model run hf.co/iRunStudio/Meltdown_GGUF
- Lemonade
How to use iRunStudio/Meltdown_GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull iRunStudio/Meltdown_GGUF
Run and chat with the model
lemonade run user.Meltdown_GGUF-{{QUANT_TAG}}List all available models
lemonade list
- Hermes Agent
How to use iRunStudio/Meltdown_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 iRunStudio/Meltdown_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 iRunStudio/Meltdown_GGUF
Run Hermes
hermes
- Atomic Chat
| { | |
| "benchmark": "ape_compliance", | |
| "eval_set": "C:\\Users\\jassi\\Desktop\\ProGPT\\models\\meltdown_q8\\benchmarks\\data\\meltdown_ape_eval50.jsonl", | |
| "scoring": "harness-aware (partial tool_call tags tolerated per PARSING_REFERENCE.md)", | |
| "n": 20, | |
| "passes": 12, | |
| "accuracy": 60.0, | |
| "by_category": { | |
| "action_first": { | |
| "passes": 0, | |
| "total": 1, | |
| "accuracy": 0.0 | |
| }, | |
| "chat_direct": { | |
| "passes": 0, | |
| "total": 4, | |
| "accuracy": 0.0 | |
| }, | |
| "chat_tool": { | |
| "passes": 0, | |
| "total": 1, | |
| "accuracy": 0.0 | |
| }, | |
| "code_edit": { | |
| "passes": 2, | |
| "total": 2, | |
| "accuracy": 100.0 | |
| }, | |
| "edge_case": { | |
| "passes": 1, | |
| "total": 2, | |
| "accuracy": 50.0 | |
| }, | |
| "file_edit": { | |
| "passes": 1, | |
| "total": 2, | |
| "accuracy": 50.0 | |
| }, | |
| "file_response": { | |
| "passes": 1, | |
| "total": 1, | |
| "accuracy": 100.0 | |
| }, | |
| "file_system": { | |
| "passes": 2, | |
| "total": 2, | |
| "accuracy": 100.0 | |
| }, | |
| "image_response": { | |
| "passes": 1, | |
| "total": 1, | |
| "accuracy": 100.0 | |
| }, | |
| "info_retrieval": { | |
| "passes": 2, | |
| "total": 2, | |
| "accuracy": 100.0 | |
| }, | |
| "multi_step": { | |
| "passes": 2, | |
| "total": 2, | |
| "accuracy": 100.0 | |
| } | |
| }, | |
| "results": [ | |
| { | |
| "index": 0, | |
| "category": "file_system", | |
| "user": "On Mac, create /Users/developer/Documents/iRun/Projects/scratch_21/output.txt", | |
| "expect_tool": true, | |
| "has_assess": true, | |
| "has_plan": true, | |
| "has_execute": true, | |
| "assess_closed": true, | |
| "plan_closed": true, | |
| "execute_closed": false, | |
| "ape_protocol": true, | |
| "tool_call_detected": true, | |
| "tool_call_complete": false, | |
| "tool_name_valid": true, | |
| "tool_json_parseable": true, | |
| "path_match": true, | |
| "pass": true, | |
| "tool_name": "wf", | |
| "note": "tool_call truncated by server stop (harness should continue)" | |
| }, | |
| { | |
| "index": 1, | |
| "category": "file_system", | |
| "user": "Replace OLD_API_KEY with NEW_API_KEY in C:\\Users\\jassi\\Documents\\ProGPT\\Billa\\.env", | |
| "expect_tool": true, | |
| "has_assess": true, | |
| "has_plan": true, | |
| "has_execute": true, | |
| "assess_closed": true, | |
| "plan_closed": true, | |
| "execute_closed": false, | |
| "ape_protocol": true, | |
| "tool_call_detected": true, | |
| "tool_call_complete": false, | |
| "tool_name_valid": true, | |
| "tool_json_parseable": true, | |
| "path_match": true, | |
| "pass": true, | |
| "tool_name": "ef", | |
| "note": "tool_call truncated by server stop (harness should continue)" | |
| }, | |
| { | |
| "index": 2, | |
| "category": "info_retrieval", | |
| "user": "What's the weather in Seattle right now?", | |
| "expect_tool": true, | |
| "has_assess": true, | |
| "has_plan": true, | |
| "has_execute": true, | |
| "assess_closed": true, | |
| "plan_closed": true, | |
| "execute_closed": false, | |
| "ape_protocol": true, | |
| "tool_call_detected": true, | |
| "tool_call_complete": false, | |
| "tool_name_valid": true, | |
| "tool_json_parseable": true, | |
| "path_match": true, | |
| "pass": true, | |
| "tool_name": "ws", | |
| "note": "tool_call truncated by server stop (harness should continue)" | |
| }, | |
| { | |
| "index": 3, | |
| "category": "info_retrieval", | |
| "user": "Read what's on my clipboard (Windows).", | |
| "expect_tool": true, | |
| "has_assess": true, | |
| "has_plan": true, | |
| "has_execute": true, | |
| "assess_closed": true, | |
| "plan_closed": true, | |
| "execute_closed": false, | |
| "ape_protocol": true, | |
| "tool_call_detected": true, | |
| "tool_call_complete": false, | |
| "tool_name_valid": true, | |
| "tool_json_parseable": true, | |
| "path_match": true, | |
| "pass": true, | |
| "tool_name": "cb", | |
| "note": "tool_call truncated by server stop (harness should continue)" | |
| }, | |
| { | |
| "index": 4, | |
| "category": "multi_step", | |
| "user": "Code check 9: py compute square, memo result, read memo back.", | |
| "expect_tool": true, | |
| "has_assess": true, | |
| "has_plan": true, | |
| "has_execute": true, | |
| "assess_closed": true, | |
| "plan_closed": true, | |
| "execute_closed": false, | |
| "ape_protocol": true, | |
| "tool_call_detected": true, | |
| "tool_call_complete": false, | |
| "tool_name_valid": true, | |
| "tool_json_parseable": true, | |
| "path_match": true, | |
| "pass": true, | |
| "tool_name": "py", | |
| "note": "tool_call truncated by server stop (harness should continue)" | |
| }, | |
| { | |
| "index": 5, | |
| "category": "multi_step", | |
| "user": "Backup workflow 8: timestamp, write backup_8.log, append completion line.", | |
| "expect_tool": true, | |
| "has_assess": true, | |
| "has_plan": true, | |
| "has_execute": true, | |
| "assess_closed": true, | |
| "plan_closed": true, | |
| "execute_closed": false, | |
| "ape_protocol": true, | |
| "tool_call_detected": true, | |
| "tool_call_complete": false, | |
| "tool_name_valid": true, | |
| "tool_json_parseable": true, | |
| "path_match": true, | |
| "pass": true, | |
| "tool_name": "wf", | |
| "note": "tool_call truncated by server stop (harness should continue)" | |
| }, | |
| { | |
| "index": 6, | |
| "category": "edge_case", | |
| "user": "Call unknown_tool with param foo=bar.", | |
| "expect_tool": true, | |
| "has_assess": true, | |
| "has_plan": true, | |
| "has_execute": true, | |
| "assess_closed": true, | |
| "plan_closed": true, | |
| "execute_closed": false, | |
| "ape_protocol": true, | |
| "tool_call_detected": false, | |
| "tool_call_complete": false, | |
| "tool_name_valid": false, | |
| "tool_json_parseable": false, | |
| "path_match": false, | |
| "pass": false, | |
| "tool_name": null | |
| }, | |
| { | |
| "index": 7, | |
| "category": "edge_case", | |
| "user": "Read C:\\Users\\jassi\\Documents\\ProGPT\\Billa\\secret_vault\\credentials.txt", | |
| "expect_tool": true, | |
| "has_assess": true, | |
| "has_plan": true, | |
| "has_execute": true, | |
| "assess_closed": true, | |
| "plan_closed": true, | |
| "execute_closed": false, | |
| "ape_protocol": true, | |
| "tool_call_detected": true, | |
| "tool_call_complete": false, | |
| "tool_name_valid": true, | |
| "tool_json_parseable": true, | |
| "path_match": true, | |
| "pass": true, | |
| "tool_name": "rf", | |
| "note": "tool_call truncated by server stop (harness should continue)" | |
| }, | |
| { | |
| "index": 8, | |
| "category": "code_edit", | |
| "user": "In C:\\Users\\jassi\\Documents\\ProGPT\\Billa\\model_24.py swap class name OldModel for NewModel.", | |
| "expect_tool": true, | |
| "has_assess": true, | |
| "has_plan": true, | |
| "has_execute": true, | |
| "assess_closed": true, | |
| "plan_closed": true, | |
| "execute_closed": false, | |
| "ape_protocol": true, | |
| "tool_call_detected": true, | |
| "tool_call_complete": false, | |
| "tool_name_valid": true, | |
| "tool_json_parseable": true, | |
| "path_match": true, | |
| "pass": true, | |
| "tool_name": "ef", | |
| "note": "tool_call truncated by server stop (harness should continue)" | |
| }, | |
| { | |
| "index": 9, | |
| "category": "code_edit", | |
| "user": "In C:\\Users\\jassi\\Documents\\ProGPT\\Billa\\src\\api_4.py, point api to production url.", | |
| "expect_tool": true, | |
| "has_assess": true, | |
| "has_plan": true, | |
| "has_execute": true, | |
| "assess_closed": true, | |
| "plan_closed": true, | |
| "execute_closed": false, | |
| "ape_protocol": true, | |
| "tool_call_detected": true, | |
| "tool_call_complete": false, | |
| "tool_name_valid": true, | |
| "tool_json_parseable": true, | |
| "path_match": true, | |
| "pass": true, | |
| "tool_name": "ef", | |
| "note": "tool_call truncated by server stop (harness should continue)" | |
| }, | |
| { | |
| "index": 10, | |
| "category": "file_edit", | |
| "user": "Overwrite C:\\Users\\jassi\\Documents\\ProGPT\\Billa\\app_18.config \u2014 set debug=true only.", | |
| "expect_tool": true, | |
| "has_assess": true, | |
| "has_plan": true, | |
| "has_execute": true, | |
| "assess_closed": true, | |
| "plan_closed": true, | |
| "execute_closed": false, | |
| "ape_protocol": true, | |
| "tool_call_detected": true, | |
| "tool_call_complete": false, | |
| "tool_name_valid": true, | |
| "tool_json_parseable": true, | |
| "path_match": true, | |
| "pass": true, | |
| "tool_name": "ef", | |
| "note": "tool_call truncated by server stop (harness should continue)" | |
| }, | |
| { | |
| "index": 11, | |
| "category": "file_edit", | |
| "user": "Mark doc section complete. in C:\\Users\\jassi\\Documents\\ProGPT\\Billa\\docs\\guide_3.md", | |
| "expect_tool": true, | |
| "has_assess": true, | |
| "has_plan": true, | |
| "has_execute": true, | |
| "assess_closed": true, | |
| "plan_closed": true, | |
| "execute_closed": false, | |
| "ape_protocol": true, | |
| "tool_call_detected": true, | |
| "tool_call_complete": false, | |
| "tool_name_valid": true, | |
| "tool_json_parseable": false, | |
| "path_match": true, | |
| "pass": false, | |
| "tool_name": "wf", | |
| "note": "tool_call truncated by server stop (harness should continue)" | |
| }, | |
| { | |
| "index": 12, | |
| "category": "file_response", | |
| "user": "Analyze C:\\Users\\jassi\\Documents\\ProGPT\\Billa\\metrics_10.csv \u2014 what's the trend?", | |
| "expect_tool": true, | |
| "has_assess": true, | |
| "has_plan": true, | |
| "has_execute": true, | |
| "assess_closed": true, | |
| "plan_closed": true, | |
| "execute_closed": false, | |
| "ape_protocol": true, | |
| "tool_call_detected": true, | |
| "tool_call_complete": false, | |
| "tool_name_valid": true, | |
| "tool_json_parseable": true, | |
| "path_match": true, | |
| "pass": true, | |
| "tool_name": "rc", | |
| "note": "tool_call truncated by server stop (harness should continue)" | |
| }, | |
| { | |
| "index": 13, | |
| "category": "image_response", | |
| "user": "[Attached image context]\nScreenshot of failing test: Expected '200' got '500' on /api/health.\n\nCheck the health handler.", | |
| "expect_tool": true, | |
| "has_assess": true, | |
| "has_plan": true, | |
| "has_execute": true, | |
| "assess_closed": true, | |
| "plan_closed": true, | |
| "execute_closed": false, | |
| "ape_protocol": true, | |
| "tool_call_detected": true, | |
| "tool_call_complete": false, | |
| "tool_name_valid": true, | |
| "tool_json_parseable": true, | |
| "path_match": true, | |
| "pass": true, | |
| "tool_name": "rc", | |
| "note": "tool_call truncated by server stop (harness should continue)" | |
| }, | |
| { | |
| "index": 14, | |
| "category": "action_first", | |
| "user": "Schedule a meeting tomorrow 3pm with the team.", | |
| "expect_tool": true, | |
| "has_assess": true, | |
| "has_plan": true, | |
| "has_execute": false, | |
| "assess_closed": true, | |
| "plan_closed": false, | |
| "execute_closed": false, | |
| "ape_protocol": false, | |
| "tool_call_detected": false, | |
| "tool_call_complete": false, | |
| "tool_name_valid": false, | |
| "tool_json_parseable": false, | |
| "path_match": false, | |
| "pass": false, | |
| "tool_name": null | |
| }, | |
| { | |
| "index": 15, | |
| "category": "chat_direct", | |
| "user": "Thanks for fixing that!", | |
| "expect_tool": false, | |
| "has_assess": false, | |
| "has_plan": false, | |
| "has_execute": true, | |
| "assess_closed": false, | |
| "plan_closed": false, | |
| "execute_closed": true, | |
| "ape_protocol": false, | |
| "tool_call_detected": false, | |
| "tool_call_complete": false, | |
| "tool_name_valid": false, | |
| "tool_json_parseable": false, | |
| "path_match": true, | |
| "pass": false, | |
| "tool_name": null | |
| }, | |
| { | |
| "index": 16, | |
| "category": "chat_direct", | |
| "user": "What does Response path mean in Meltdown?", | |
| "expect_tool": false, | |
| "has_assess": false, | |
| "has_plan": false, | |
| "has_execute": false, | |
| "assess_closed": false, | |
| "plan_closed": false, | |
| "execute_closed": false, | |
| "ape_protocol": false, | |
| "tool_call_detected": false, | |
| "tool_call_complete": false, | |
| "tool_name_valid": false, | |
| "tool_json_parseable": false, | |
| "path_match": true, | |
| "pass": false, | |
| "tool_name": null | |
| }, | |
| { | |
| "index": 17, | |
| "category": "chat_direct", | |
| "user": "Is my data sent to the cloud?", | |
| "expect_tool": false, | |
| "has_assess": true, | |
| "has_plan": true, | |
| "has_execute": true, | |
| "assess_closed": true, | |
| "plan_closed": true, | |
| "execute_closed": false, | |
| "ape_protocol": true, | |
| "tool_call_detected": true, | |
| "tool_call_complete": false, | |
| "tool_name_valid": true, | |
| "tool_json_parseable": true, | |
| "path_match": false, | |
| "pass": false, | |
| "tool_name": "mp" | |
| }, | |
| { | |
| "index": 18, | |
| "category": "chat_direct", | |
| "user": "Can you append to journals?", | |
| "expect_tool": false, | |
| "has_assess": true, | |
| "has_plan": true, | |
| "has_execute": true, | |
| "assess_closed": true, | |
| "plan_closed": true, | |
| "execute_closed": false, | |
| "ape_protocol": true, | |
| "tool_call_detected": true, | |
| "tool_call_complete": false, | |
| "tool_name_valid": true, | |
| "tool_json_parseable": true, | |
| "path_match": false, | |
| "pass": false, | |
| "tool_name": "wf" | |
| }, | |
| { | |
| "index": 19, | |
| "category": "chat_tool", | |
| "user": "Append line run_24 to C:\\Users\\jassi\\Documents\\ProGPT\\Billa\\journal.txt", | |
| "expect_tool": true, | |
| "has_assess": false, | |
| "has_plan": false, | |
| "has_execute": false, | |
| "assess_closed": false, | |
| "plan_closed": false, | |
| "execute_closed": false, | |
| "ape_protocol": false, | |
| "tool_call_detected": true, | |
| "tool_call_complete": false, | |
| "tool_name_valid": true, | |
| "tool_json_parseable": true, | |
| "path_match": true, | |
| "pass": false, | |
| "tool_name": "wf" | |
| } | |
| ] | |
| } |