Perplexity Computer · News date: · WATCH
Type: Computer-Use Agent
Perplexity open-sources the local engine behind its hybrid compute feature
Your move: Matters mainly if you use hybrid compute on a Mac or build on top of it
On September 2, 2026, Perplexity open-sourced Lily, the local inference engine that runs the on-device half of Perplexity Computer's hybrid compute feature on Mac. Lily is built specifically to run the Qwen3.6-35B-A3B model on Apple silicon, using a Rust and Metal setup instead of general-purpose tools like Apple's MLX. In Perplexity's own tests on an M5 Max Mac, it processed prompts about 23% faster and generated text about 35% faster than MLX-LM, and needs at least 32GB of memory to run.
Why it matters
This doesn't change what Perplexity Computer can do for most users today, it's the engine running under the hood, not a new feature. It matters if you're curious how the local half of hybrid compute works, or you want to run the same model yourself outside Perplexity's app.
Source: MarkTechPost ↗
Published by Agent Log. The summary reports the linked source; “Why it matters” and the verdict are Agent Log's interpretation.
More Perplexity Computer updates →