{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreigqrl5qeepxqazugylvad3davpsndcg3esclmvtiuxfssihpssmr4",
    "uri": "at://did:plc:azwgjkqilqtufnhrpl2oxmkw/app.bsky.feed.post/3mngkfxllf7y2"
  },
  "coverImage": {
    "$type": "blob",
    "ref": {
      "$link": "bafkreihivb6antrl64fkzw5n6as2kj5qxviiaeqn26djjtkl67isj64m5a"
    },
    "mimeType": "image/png",
    "size": 409465
  },
  "path": "/2026/06/google-gemma-4-12b-local-ai/",
  "publishedAt": "2026-06-04T02:06:24.000Z",
  "site": "https://nerds.xyz",
  "tags": [
    "Google",
    "Artificial Intelligence",
    "AI",
    "Apache 2.0",
    "artificial intelligence",
    "Gemma 4 12B",
    "Linux",
    "local AI",
    "machine learning",
    "multimodal AI",
    "Open Source"
  ],
  "textContent": "Google is pitching Gemma 4 12B as a multimodal AI model powerful enough for agentic workflows while still being lightweight enough to run locally on consumer laptops with 16GB of memory. The company’s encoder-free design could make this one of its more interesting AI releases yet.",
  "title": "Google wants your next AI agent running locally on a 16GB laptop"
}