Perplexity open-sources Lily, its Apple Silicon inference engine for Qwen3.6-35B-A3B

inductionheads · x · 2026-09-03

Perplexity has open-sourced Lily, the local inference engine powering its new hybrid compute feature in the Mac app. Lily is specialized for Qwen3.6-35B-A3B on Apple silicon, built so on-device compute doesn't bottleneck Computer tasks, splitting work between local and cloud.

Related event: Perplexity Open-Sources Lily, a Qwen3.6 Inference Engine for Apple Silicon(8 posts)→

Original post →

More from Infra

Infra channel →