| Signal | Result | Reference |
|---|---|---|
| Tokenizer signature | Not measured | – |
| API surface | Identical contract to 2 other entries | api_130ec2d7 |
| Context and output | 131,072 context · 16,384 max output | declared |
| Reasoning contract | None declared | declared |
| Serving providers observed | None recorded yet | – |
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...
Supported parameters
frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetop_ktop_p
defaults: {}
Cite this page as the evidence record for Google: Gemma 3 4B: the URL is stable, measurements are dated, and revisions append to the history above. Method: tokenizer fingerprinting, v1, 50 strings. The raw data behind every figure is on the data page.
