Perplexity has built a local artificial intelligence engine designed specifically for Apple silicon and the Qwen3.6-35B-A3B model. ^[1] Perplexity says it plans to release Lily as open source, but the code is not available yet. ^[2] Perplexity says Lily averaged 23 percent faster prompt processing and 35 percent faster token generation than MLX-LM on an M5 Max MacBook Pro with 128GB of unified memory. ^[3] The engine, called Lily, uses a Rust runtime and custom Metal kernels, with neither PyTorch nor MLX in its execution path. ^[4] For a 203 GiB model (Llama-4-Scout), weights loading from S3 dominates startup time at approximately 423 seconds (92%), while torch.compile takes only 34 seconds (8%). ^[5] Subsequent launches on the same node for a 64 GiB model were reduced from 82 seconds to 16 seconds after configuration changes. ^[6]