Perplexity @perplexity_ai · 02 Sep 2026
Today we’re open-sourcing Lily, the local inference engine we built for hybrid compute in Perplexity Computer. Lily is specialized for Qwen3.6-35B-A3B on Apple silicon, built so on-device compute doesn’t bottleneck Computer tasks. Read more: https://t.co/OnowTP3ql6
207 078Views
1 587Likes
146Reposts
57Replies
39Quotes
1 088Bookmarks
Is that a lot?
1.47×vs this author's median140 997 views is typical
50Percentile for this authorof 6 recent posts
9.27×vs 100K–1M median22 338 views is typical
41.20%Reachviews ÷ followers
0.88%Engagement rateof viewers reacted