google / gemma-2 family / text-generation
gemma-2-9b
google/gemma-2-9b
Benchmarks
Where it scores.
General Provisional —
Coding Provisional —
Math Provisional —
Reasoning Provisional —
Normalized 0–100 across indexed models.
Runnable variants
Pick a size.
| Precision | Format | Size | Params | File |
|---|---|---|---|---|
| FP16 / smallest | SAFETENSORS | 2.4 GB | — | model-00008-of-00008.safetensors |
| FP16 | SAFETENSORS | 4.8 GB | — | model-00001-of-00008.safetensors |
| FP16 | SAFETENSORS | 4.9 GB | — | model-00004-of-00008.safetensors |
| FP16 | SAFETENSORS | 5.0 GB | — | model-00002-of-00008.safetensors |
| FP16 | SAFETENSORS | 5.0 GB | — | model-00005-of-00008.safetensors |
| FP16 | SAFETENSORS | 5.0 GB | — | model-00006-of-00008.safetensors |
| FP16 | SAFETENSORS | 5.0 GB | — | model-00003-of-00008.safetensors |
| FP16 | SAFETENSORS | 5.0 GB | — | model-00007-of-00008.safetensors |
Sizes are file sizes, not peak runtime memory.
From the Hugging Face model card
About this model.
From the Hugging Face model card