§ feed · storyline

Optimizing On-Device Inference for Apple Silicon

Perplexity releases Lily, a local inference engine optimized for running large models on Apple silicon.

Sep 2 · 02:00:00 · primary fetch1 sourceupdated Sep 2 · 02:00:00

Perplexity detailed its Lily local inference engine, optimized specifically for Apple silicon to enable high-performance, on-device AI tasks for models like Qwen3.6-35B-A3B.

read full article on perplexity.ai ↗

§ sources1 publication · timeline below

perplexity.aiOptimizing On-Device Inference for Apple Siliconprimary02:00:00