Gemma 4 E2B in Pure JAX on a Colab TPU: Google's 4-Bit Export Against an Exact Repack
DEV Community
Gemma 4 E2B in Pure JAX on a Colab TPU: Google's 4-Bit Export Against an Exact Repack
A Colab notebook for the AI GDE Marathon that loads three Gemma 4 E2B checkpoints into a pure-JAX engine on one TPU v5e chip and measures, on the reader's own chip, how far each 4-bit build sits from the weights Google trained. The repack holds the trained grid and comes out 342.6x closer to the QAT model at the same speed and a smaller download.
0 comments
No comments yet.