tijs/local-model-bench
Reproducible local LLM benchmarks on affordable Apple Silicon Macs: synthetic Peixinho workflows, isolated Python automation, tool use, speed, memory and cache behavior with Mei/MLX and llama.cpp.
GitHub repository with 9 stars and 0 forks.
Language: Python
Topics: apple-silicon, benchmarking, llama-cpp, llm-evaluation, local-llm, mlx, tool-calling