{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreifmbg5bzlni2ejqespmmfrn733yahlmryyl7ffmsjdioshrv5jqka",
    "uri": "at://did:plc:piu6o3yjztvb2lzpxqeerabi/app.bsky.feed.post/3mie4kh4b42y2"
  },
  "coverImage": {
    "$type": "blob",
    "ref": {
      "$link": "bafkreic6scf7pefctptsjsyaiegqxhsh2z667jkrwhthfovwzmkmoitzqm"
    },
    "mimeType": "image/jpeg",
    "size": 69680
  },
  "path": "/2026/03/31/ollama-now-runs-faster-apple-silicon-macs/",
  "publishedAt": "2026-03-31T03:22:24.000Z",
  "site": "https://www.macrumors.com",
  "tags": [
    "Apple",
    "Rumors",
    "Mac",
    "iOS",
    "iPhone",
    "iPad",
    "Ollama",
    "MLX",
    "According to Ollama",
    "available to download as Ollama 0.19",
    "Alibaba's Qwen3.5",
    "Ollama Now Runs Faster on Macs Thanks to Apple's MLX Framework",
    "MacRumors.com",
    "Discuss this article"
  ],
  "textContent": "Ollama, the popular app for running AI models locally on a computer, has released an update that takes advantage of Apple's own machine learning framework, MLX. The result is a hefty speed boost on Macs with Apple silicon.\n\n\nAccording to Ollama, the new version processes prompts around 1.6 times faster (prefill speed) and nearly doubles the speed at which it generates responses (decode speed). Macs with M5-series chips are said to see the largest improvements, thanks to Apple's new GPU Neural Accelerators.\n\nThe update also includes smarter memory management, which should make AI-powered coding tools and chat assistants feel noticeably more responsive during extended use.\n\nOllama says the new performance boost should especially benefit macOS users who run personal assistants like OpenClaw or coding agents like Claude Code, OpenCode, or Codex.\n\nThe preview release is available to download as Ollama 0.19 – just make sure you have a Mac with more than 32GB of unified memory to run it. Support is currently limited to Alibaba's Qwen3.5, but Ollama says support for more AI models is planned.\nThis article, \"Ollama Now Runs Faster on Macs Thanks to Apple's MLX Framework\" first appeared on MacRumors.com\n\nDiscuss this article in our forums\n\n",
  "title": "Ollama Now Runs Faster on Macs Thanks to Apple's MLX Framework"
}