Perplexity Open Sources Lily: A Rust + Metal Inference Engine for Qwen3.6-35B-A3B on Apple Silicon

Perplexity has released Lily, an open-source inference engine developed in Rust with custom Metal kernels designed specifically to run Qwen3.6-35B-A3B on Apple Silicon. By optimizing performance for this specific model and chip architecture, the engine achieves faster prefill and decode throughput compared to the existing MLX-LM framework.