ai.paski.devGemma 3 27B Instruct
llmGoogle's instruction-tuned open-weights multimodal model, the largest single-accelerator-deployable model in the Gemma 3 family.
Metadata
| org | |
| released | 2025-03-12 |
| params | 27B |
| license | gemma |
| kind | llm |
| hf id | google/gemma-3-27b-it |
Benchmarks
| MMLU | 76.9 | source ↗ |
| MMLU-Pro | 67.5 | source ↗ |
| GPQA | 42.4 | source ↗ |
| HumanEval | 87.8 | source ↗ |
Lineage
No recorded lineage — root or standalone model.
view in full graph →