apple-silicon-llm-bench
john-rocky
Reproducible on-device LLM benchmarks for Apple Silicon (iPhone 17 Pro, M4 Max): Apple Core AI, MLX, llama.cpp, LiteRT-LM and Core ML on the same model and harness, every number with its quantization and capture session; hybrid Mamba-2 models (Nemotron-3 Nano, Granite-4.0-H, Falcon-H1) included.
Growth over time
3 data points · 2026-07-27 → 2026-09-08How do you feel about this project?
Ask AI about apple-silicon-llm-bench
Question copied to clipboardWhat is the john-rocky/apple-silicon-llm-bench GitHub project? Description: "Reproducible on-device LLM benchmarks for Apple Silicon (iPhone 17 Pro, M4 Max): Apple Core AI, MLX, llama.cpp, LiteRT-LM and Core ML on the same model and harness, every number with its quantization and capture session; hybrid Mamba-2 models (Nemotron-3 Nano, Granite-4.0-H, Falcon-H1) included.". Written in Python. Explain what it does, its main use cases, key features, and who would benefit from using it.
Question is copied to clipboard — paste it after the AI opens.
How to clone apple-silicon-llm-bench
Clone via HTTPS
Clone via SSH
Download ZIP
Download main.zipFound an issue?
Report bugs or request features on the apple-silicon-llm-bench issue tracker:
Open GitHub Issues