leeyunseokarchive/fituna
Stop guessing your llama.cpp config. Give it a target tok/s and a quality budget, and it measures quantization levels and GPU offload on your own machine to find the lightest setup that actually hits the target.
GitHub repository with 6 stars and 10 forks.
Language: Python
Topics: benchmarking, cli, gguf, llama-cpp, llm, llm-inference, local-llm, mcp, python, quantization