google
/

gemma-4-12B-it-qat-w4a16-ct

image-text-to-text

compressed-tensors

Model card Files Files and versions

Resources

View closed (5)

Raise per-image vision soft-token budget from 280 to 1120

#8 opened 16 days ago by

lucianommartins

Google, Open Source Old Bison PaLM 2 Model In 2026/27

#6 opened about 1 month ago by

vLLM Help

#3 opened about 2 months ago by

Tested it and its the Bomb! Vram efficient with high Quality.

#2 opened about 2 months ago by

unable to save AOT compiled function

#1 opened about 2 months ago by