gemma-4-12B-it-qat-q4_0-unquantized

Checkpointgoogle/gemma-4-12B-it-qat-q4_0-unquantizedModel card indexedModel card

Support summary

gemma-4-12B-it-qat-q4_0-unquantized is a checkpoint published by Google, built on the Gemma4UnifiedForConditionalGeneration architecture. vLLM lists its architecture, but not this exact checkpoint.

Configured context: 262,144 tokens
License: apache-2.0

Hugging Face model card

Publisher: Google
Task: any to any
License: apache-2.0
Library: transformers
Architecture: Gemma4UnifiedForConditionalGeneration
Weight tensor elements: 12B
Tensor types: BF16
Configured context: 262,144 tokens
Base models: google/gemma-4-12B-it
Weight access: Public
Repository created: 2026-06-04

Source 1 Source 2 Source 3Reviewed 2026-09-05

Model notes and sources

Engine support

3 engines

Engine support for gemma-4-12B-it-qat-q4_0-unquantized
Engine	Release	Evidence scope	Last known supported
vLLM	`0.28.0`Newest indexed	Architecture listed; exact checkpoint unknown	No supported release indexed
Features, dependencies and evidence for vLLM 0.28.0
SGLang	`0.5.19`Newest indexed	No matching evidence curated	No supported release indexed
Features, dependencies and evidence for SGLang 0.5.19
TensorRT-LLM	`1.2.1`Newest indexed	No matching evidence curated	No supported release indexed
Features, dependencies and evidence for TensorRT-LLM 1.2.1