{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreiemvwwlm6gk5b27hti2viltzfdg2repmhhxrjr3a55sbhmlu5mp7u",
    "uri": "at://did:plc:bbwgwecw2vdijmj42eealwtt/app.bsky.feed.post/3mlaatajer2e2"
  },
  "coverImage": {
    "$type": "blob",
    "ref": {
      "$link": "bafkreieslqxaohzweyaf5vedmmli7qxkgnfx6sau35inpdujkswdpqvzpu"
    },
    "mimeType": "image/webp",
    "size": 30022
  },
  "path": "/google-made-gemma-4-models-3x-faster-with-mtp-drafters/",
  "publishedAt": "2026-05-06T20:35:09.000Z",
  "site": "https://www.testingcatalog.com",
  "tags": [
    "Gemini News",
    "Latest AI News",
    "AI Announcements"
  ],
  "textContent": "What's new? Speculative decoding pairs a heavy main model with a light drafter to pre-generate tokens; Gemma 4 models now run on consumer GPUs and edge devices;",
  "title": "Google made Gemma 4 models 3x faster with MTP Drafters"
}