gemma-4-12b-it — VINDEX3

google/gemma-4-12B-it encoded as a VINDEX3 container for LARQL: the original BF16 weights, unmodified, plus the model's structure as an executable, inspectable graph.

larql pull larql/gemma-4-12b-it
larql run gemma-4-12b-it "What is the capital of France?"
larql serve gemma-4-12b-it --port 8080      # OpenAI-compatible API

Supported: text generation (run, chat, serve, LQL, vindex3 observe). The vision and audio weights are carried in the container, but this LARQL build does not admit image or audio input for this model.

Encoded from google/gemma-4-12B-it@43c9d014b231474fa7212dbb48a762566c2b255d. Verification and digests are in PROVENANCE.md.

License

Gemma 4 is released by Google under the Apache License 2.0 (https://ai.google.dev/gemma/docs/gemma_4_license). This container redistributes the original weights unmodified under that license.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for larql/gemma-4-12b-it

Base model

google/gemma-4-12B

Finetuned

google/gemma-4-12B-it

Finetuned

(301)

this model