Google: Gemma 3 27B is Google's model. Its measured tokenizer sits with the Gemini group, which is evidence that it builds on the Gemini tokenizer. Tokenizer reuse is normal engineering, open vocabularies travel between labs, and this says nothing against Google's authorship of the model itself.
| Signal | Result | Reference |
|---|---|---|
| Tokenizer signature | Exact match with 6 other models | tk_59ca250f |
| API surface | No other entry shares this exact contract | api_34d4f917 |
| Context and output | 262,144 context · 131,072 max output | declared |
| Reasoning contract | None declared | declared |
| Serving providers observed | DeepInfra | measured 21 August 2026 |
Click a row to open the full comparison.
An x marks a row excluded as corrupt (caching or provider interference detected during measurement). Overhead subtracted: 9 prompt tokens.
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_biaslogprobsmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
defaults: {"temperature":null,"top_p":null,"frequency_penalty":null}
Cite this page as the evidence record for Google: Gemma 3 27B: 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.
