apple-silicon-llm-bench

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 harn

What is apple-silicon-llm-bench?

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.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/john-rockyapple-silicon-llm-bench.svg)](https://yunodb.com/tools/john-rockyapple-silicon-llm-bench?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/john-rockyapple-silicon-llm-bench?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/john-rockyapple-silicon-llm-bench.svg" alt="Featured on YunoDB" height="20"></a>