Perplexity has open sourced Lily, a Rust and Metal-based local inference engine designed for Apple Silicon, outperforming MLX-LM in throughput.
1 editorial report · 2 verified social mentions. The most authoritative report leads while later evidence completes the story.
Today we’re open-sourcing Lily, the local inference engine we built for hybrid compute in Perplexity Computer. Lily is specialized for Qwen3.6-35B-A3B on Apple silicon, built so on-device compute doesn’t bottleneck Computer tasks. Read more: https://www.perplexity.ai/hub/blog/optimizing-on-device-inference-for-apple-silicon
Open mention📰 Perplexity Will Open Source Its Faster Lily AI Engine For Apple Silicon BrianFagioli writes: Perplexity has built a local artificial intelligence engine designed specifically for Apple silicon and the Qwen3.6-35B-A3B model. Called Lily, the engine uses a Rust runtime a... 📰 Source: Slashdot 🔗 Link: https://entertainment.slashdot.org/story/26/09/02/2235237/perplexity-will-open-source-its-faster-lily-ai-engine-for-apple-silicon?utm_source=rss1.0mainlinkanon&utm_medium=feed # AI # ArtificialIntelligence
Open mention