Gemma 4 12B

EXL3 3 bpw · tabbyapi · 128K context · RTX 2000 Ada · 16 GB

Google's Gemma 4 12B from May 2026: a compact multimodal model with thinking, good with images and documents.

– tok/sdecode

– tok/sprefill

128Kcontext window

Earlier checkearlier

Run it

Follow the steps below to download and run this recipe. Omarchy Local AI lists the recipes it can launch on your hardware. The server then answers on http://localhost:8000/v1.

1 Download the weights

hf download turboderp/gemma-4-12B-it-exl3 \
  --revision 38309570753c5fde71a818feb513b1e09a81fc18 \
  --local-dir ~/models/gemma-4-12B-it-exl3-38309570

2 Start the server

docker run --rm \
  --gpus all \
  -p 8000:5000 \
  --network host \
  --shm-size 8g \
  -e NVIDIA_VISIBLE_DEVICES=all \
  -v ~/models/gemma-4-12B-it-exl3-38309570:/workspace/models:ro \
  --entrypoint /opt/venv/bin/python3 \
  ghcr.io/theroyallab/tabbyapi:cu13@sha256:ffa8388f310d3c8a2727c66d14a76bb663fdb99a2a49e68a43c3bebb5a3e53f1 \
  main.py \
  --config /app/config.yml

What it passed

✓ loadLoads and serves within an hour

✓ chatAnswers a plain question and stops on its own

– reasoningThinks separately and gets 17 × 23 right

– toolsCalls a tool with the right arguments and uses the result

– contextRecalls a code buried in a prompt that fills 85% of the window

– speedDecodes at 15 tok/s or more

Passed the older check (loads and chats); a full six-check run is pending.

Details

Weights: turboderp/gemma-4-12B-it-exl3 @ 3830957075 ›
Image: ghcr.io/theroyallab/tabbyapi:cu13@sha256:ffa8388f310d3c8a2727c66d14a76bb663fdb99a2a49e68a43c3bebb5a3e53f1
Launch: tabbyapi-gemma-4-12b-3-bpw-128k ›
Recipe file: registry/recipes/nvidia/rtx-2000-ada-16gb/gemma-4-12b.tabbyapi.128k.json ›
Model released: May 23, 2026
Tested: earlier acceptance