{
  "id": 13276726,
  "title": "Gemma 4 E2B in Pure JAX on a Colab TPU: Google's 4-Bit Export Against an Exact Repack",
  "url": "https://urgent.news/2026/10/10/gemma-4-e2b-in-pure-jax-on-a-colab-tpu-googles-4-bit-export-against",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-10T00:51:07.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/gde/gemma-4-e2b-in-pure-jax-on-a-colab-tpu-googles-4-bit-export-against-an-exact-repack-4dle"
  },
  "original_language": "en",
  "account": null,
  "summary": "This article provides a comprehensive guide on how to run Gemma 4 E2B on a single TPU v5e chip using a pure-JAX engine on a Google Colab notebook. The notebook compares two 4-bit builds of the same model against the weights Google trained. The first build, provided by Google, is exported as gemma-4-E2B-it-qat-w4a16-ct, while the second build is a repack that stores the trained grid, resulting in a 342.6 times closer approximation to the original model in next-token predictions, and matching its top token 99.29% of the time. The notebook also highlights the differences between the two 4-bit builds and provides step-by-step instructions on how to download the three checkpoints and run the notebook on a TPU runtime.",
  "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."
}