# Perplexity open-sources Lily inference engine for Apple silicon

Lily is specialized for Qwen3.6-35B-A3B to handle local inference for hybrid compute in Perplexity Computer.

- Lily separates prefill and decode into distinct workloads to optimize memory bandwidth and weight reuse on Apple silicon.
- Benchmarks on an M5 Max MacBook Pro showed an average 1.23× higher prefill throughput and 1.35× higher decode throughput over MLX-LM.
- The code is available in the perplexityai/pplx-garden GitHub repository.

## Why it matters

Developers running Qwen models locally on Mac hardware can achieve higher throughput without sacrificing output quality.

## Sources

- [Perplexity: Perplexity open-sources Lily inference engine for Apple silicon](https://x.com/perplexity_ai/status/2095241544383226274)

---

Summarized by dstilled on 2026-09-02. https://dstilled.ai/story/b7e071aa-3011-4c56-9916-248f8194f00f