Perplexity is open-sourcing its Lily AI engine, designed for local artificial intelligence processing on Apple Silicon. The engine is built using Rust and supports the Qwen3.6-35B-A3B model, aiming to provide faster AI capabilities directly on user devices. AI
IMPACT This release could enable more efficient on-device AI processing for applications leveraging Apple Silicon.
RANK_REASON This is a product release for an AI engine, but not from a frontier lab.
Read on Mastodon — fosstodon.org →
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →