Apple shows how much faster the M5 runs local LLMs compared to the M4
SMRTR summary
Apple's new M5 chip shows significant performance improvements over the M4 when running local large language models, thanks to new GPU Neural Accelerators designed for machine learning. Using Apple's MLX framework, the M5 showed 19-27% faster text generation and completed image generation 3.8 times faster than the M4. These gains stem from the M5's increased memory bandwidth of 153GB/s compared to the M4's 120GB/s, enabling more efficient AI processing on Mac devices.
SMRTR provides this summary for quick context. The original article belongs to 9to5Mac.
Read the original article