AISlashdotabout 3 hours ago
Perplexity Open Sources Lily AI Engine for Apple Silicon
1 min read
Perplexity open sourced Lily, a Rust and Metal inference engine for Qwen3.6-35B-A3B on Apple silicon, with no PyTorch or MLX in the execution path. On an M5 Max MacBook Pro, Lily averaged 23 percent faster prompt processing and 35 percent faster token generation than MLX-LM.
Level
Hype check
Tap to vote and see what everyone thinks.
