Perplexity (@Perplexity_AI) open-sources Lily, the local inference engine built for hybrid compute in Perplexity Computer. Lily is specialized for Qwen3.6-35B-A3B on Apple silicon so on-device compute does not bottleneck Computer tasks.

Key Takeaways

  • ✓Official open-source of Lily for Perplexity Computer hybrid local/cloud compute.
  • ✓Specialized local inference for Qwen3.6-35B-A3B on Apple silicon.
  • ✓Goal: keep on-device inference from bottlenecking Computer agent tasks.
⚡

Key Decision Metrics at a Glance

TL;DR Verdict
🏆 Benchmark RankRank
See how it ranks on the leaderboard
Full Leaderboard→
💰 Cost & PlansCompare
Qwen3.6-Plus · in: $0.3 / out: $1.2
Compare Plans↗
🛠️ Ecosystem & IDERules
Cursor Composer (Agent Mode) · Claude Code (Anthropic)
Setup IDE Rules↗
🧭

Turn your technical choice into a development budget

Compare 40 dev plans & simulate token costs vs $20/mo subscriptions

⚔️ Compare Model→💰 Compare plans & limits↗
Action HubReady to adopt this in production?

Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.

⚔️ Launch VS Compare→💳 View Plans↗
Up NextPerplexity CEO shares early Gemini 4 Carbon evals: a record 0.857 on the WANDR deep-research benchmark at $5.86 per task, ahead of Argon and GPT-6 Astra
Read Now→