translategemma:4b

Upstream reference: TranslateGemma 4B IT

Publisher: Google Translate

Google describes this Gemma 3-derived model for translating text or extracting and translating text from images, using a translation-specific chat template.

Publisher-described context, separate from Sigma5C observations and recorded catalog statistics.

Published upstream specifications

Documented languages
55 Source
Published total input context
2K tokens, publisher notation Source
Image preprocessing described
896 by 896 pixels encoded to 256 tokens Source
Upstream license label
Gemma terms Source

Publisher-described uses

  • Text translation and extraction-plus-translation of text in images. Source

Reference limitations

  • The card makes no claims about unrelated capabilities. The template requires source/target language codes and only User/Assistant roles; it is not a generic chatbot interface. Source

A recorded tag and an upstream card association do not verify the deployed checkpoint, quantization, configured context or current hosted availability.

Publisher sources

Links

Recorded references do not establish downloadable weights, licensing or current availability.

4.0B
parameters
Q4_K_M
quantization
gemma3
architecture
131072
context
gemma
license
2026-01-15
released

Where translategemma:4b comes from

Company / lab

Google AI / Google DeepMind

See every model and family from this maker.

Model family

translategemma

Other versions and sizes in this line.

completionvision

Named in 1 observation page

Browse the Observatory

AI-generated & AI-scored. Every observation on this site is produced and judged by AI, and AI makes mistakes. Treat each result as a recorded observation under a declared protocol, as of its date. Method and marker legend