{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreibyxvzpstapexjgecv3a7g7243ogvld4ax2gwvwafodb5ijooyxvm",
    "uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3mkqirac3yoj2"
  },
  "path": "/t/how-to-download-a-model-and-run-it-with-ollama-locally/77317#post_20",
  "publishedAt": "2026-04-30T20:02:11.000Z",
  "site": "https://discuss.huggingface.co",
  "textContent": "Hi. It’s 2026 now, and a lot easier than anything in this thread. Step 1: Go to the App Store and download a local LLM app, such as Locally AI, Private LLM, Liquid Apollo, Solair AI, PocketPal AI, Enclave, MITHRIL, fullmoon, etc. Step 2: Open the Model menu in the app and download the model(s) you’d like to use. Most apps don’t show models that aren’t compatible with your device, but some do, so keep an eye on that. Step 3: Tweak your LLM parameters. Step 4: Enjoy! That’s it. Nice and simple.",
  "title": "How to download a model and run it with Ollama locally?"
}