Skip to headlines

AI

Perplexity Open Sources Lily: A Rust + Metal Inference Engine for Qwen3.6-35B-A3B on Apple Silicon

MarkTechPostThursday, September 3, 2026 at 6:57 AM

RedScroll Brief

Perplexity has open sourced Lily, the local inference engine behind Hybrid Compute in Perplexity Computer. Built in Rust with custom Metal kernels for one model on one chip family, it averages 1.

RedScroll Signal

Impact
High
Category
Ai
Market relevance
Moderate
Why it matters
AI developments move capital, regulation, and competitive advantage across the tech stack. Perplexity has open sourced Lily, the local inference engine behind Hybrid Compute in Perplexity Computer. Built in Rust with custom Metal kernels for one model on one chip family, it averages 1. Secondary effects may show up in markets and supply chains linked to Perplexity Open Sources and Lily.

Desk copy

RedScroll Briefing

Extractive editorial brief — not a reprint of the original

What happened

Perplexity has open sourced Lily, the local inference engine behind Hybrid Compute in Perplexity Computer. Built in Rust with custom Metal kernels for one model on one chip family, it averages 1.

Why it matters

AI developments move capital, regulation, and competitive advantage across the tech stack.

Background

MarkTechPost reported on this under ai. RedScroll surfaces the signal with an extractive brief — not a reprint of the original article. Read the source for full reporting.

Timeline

  1. MarkTechPost published: Perplexity Open Sources Lily: A Rust + Metal Inference Engine for Qwen3.6-35B-A3B on Apple Silicon

  2. Story is in today’s RedScroll edition. Follow the original source for updates.

Economic impact

Secondary effects may show up in markets and supply chains linked to Perplexity Open Sources and Lily.

More on

Related stories

Source

MarkTechPost

Original reporting by MarkTechPost. RedScroll provides an extractive briefing only.