{
  "id": 5311177,
  "title": "Perplexity Will Open Source Its Faster Lily AI Engine For Apple Silicon",
  "url": "https://urgent.news/2026/09/03/perplexity-will-open-source-its-faster-lily-ai-engine-for-apple",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-03T11:00:00.000Z",
  "source": {
    "name": "Slashdot",
    "slug": "slashdot",
    "url": "https://entertainment.slashdot.org/story/26/09/02/2235237/perplexity-will-open-source-its-faster-lily-ai-engine-for-apple-silicon"
  },
  "original_language": "en",
  "account": null,
  "summary": "BrianFagioli writes: Perplexity has built a local artificial intelligence engine designed specifically for Apple silicon and the Qwen3.6-35B-A3B model. Called Lily, the engine uses a Rust runtime and custom Metal kernels, with neither PyTorch nor MLX in its execution path. Perplexity says Lily averaged 23 percent faster prompt processing and 35 percent faster token generation than MLX-LM on an M5…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}