gemma-3-12b-it
Support summary
gemma-3-12b-it is a checkpoint published by Google, built on the Gemma3ForConditionalGeneration architecture. vLLM 0.28.0, the newest indexed vLLM release, documents support. TensorRT-LLM lists its architecture, but not this exact checkpoint.
vLLM documents support in 10 of 20 indexed releases, from 0.22.0 to 0.28.0.
- Documented hardware
- CPU
- License
- gemma
Hardware, quantization and features count only statements about this checkpoint; engine-wide capabilities are listed with each release.
Hugging Face model card
- Publisher
- Task
- image text to text
- License
- gemma
- Library
- transformers
- Architecture
- Gemma3ForConditionalGeneration
- Weight tensor elements
- 12.2B
- Tensor types
- BF16
- Base models
- google/gemma-3-12b-pt
- Weight access
- Publisher approval or terms required
- Repository created
- 2025-03-01
Model notes and sources
- vLLM v0.28.0 · docs/models/hardware_supported_models/cpu.md · 10 indexed revisions, v0.22.0 to v0.28.0
- google/gemma-3-12b-it · publisher model card
- google/gemma-3-12b-it · Hugging Face metadata
- Reviewed
Engine support
3 engines
| Engine | Release | Checkpoint support | Evidence scope | Last known supported |
|---|---|---|---|---|
| vLLM | 0.28.0Newest indexed | Checkpoint evidenceSource: vLLM v0.28.0 · docs/models/hardware_supported_models/cpu.mdReviewed | 0.28.0This release | |
Features, dependencies and evidence for vLLM 0.28.0 | ||||
| SGLang | 0.5.19Newest indexed | No matching evidence curated | No supported release indexed | |
Features, dependencies and evidence for SGLang 0.5.19 | ||||
| TensorRT-LLM | 1.2.1Newest indexed | Architecture listed; exact checkpoint unknown | No supported release indexed | |
Features, dependencies and evidence for TensorRT-LLM 1.2.1 | ||||