Language

Gemma 4 12B (QAT)

Quantization-Aware-Trained Gemma 4 12B. Higher quality than naive Q4 at the same size. MTP-enabled via `gemma4-12b-mtp-draft`.

Gemma LicenseSource verified

Specification

Model ID

gemma4-12b-qat

Family

gemma4

Modality

Language

Parameters

12B

Context

131,072 tokens

Quantization

UD-Q4_K_XL (QAT)

Weights

7.4 GB

Minimum RAM

10 GB

Source

Weights and provenance.

Repository

unsloth/gemma-4-12B-it-qat-GGUF

Registry license

Gemma License

Access

Open — weights fetch without accepting additional terms.

The licence above is the registry's. The source repository either states nothing, states the catch-all “other”, or carries a licence link and base model that its own tag contradicts — a re-quantisation inherits the terms of the weights it derives from. The registry's licence is the one to rely on.

Serve it

# Pull the weights onto a node
tenzro model download gemma4-12b-qat

# Serve it
tenzro model serve gemma4-12b-qat

# Or query the registry entry over JSON-RPC
curl https://rpc.tenzro.xyz \
  -X POST -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,
       "method":"tenzro_getModel",
       "params":[{"model_id":"gemma4-12b-qat"}]}'