Gemma 3 4B
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,...
The figures
- Made by
- Model ID
- google/gemma-3-4b-it
- Input
- $0.05 per million tokens
- Output
- $0.1 per million tokens
- Context window
- 131K tokens
- Longest answer
- 16K tokens
- Takes in
- text, image
- Gives back
- text
- Reasoning
- No
- Tool calling
- No
- Reads images
- Yes
- Open weights
- Yes
- Released
- 13 Mar 2025
Read on 3 Oct 2026.