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
- TranslateGemma 4B IT official documentation — Google Translate. Checked .
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