Google: Gemma 3 4B (free)
Google Gemma 3 4B (free) is the smallest and weakest of the Gemma 3 family, with very low benchmark scores across all dimensions — it is best suited to extremely lightweight or experimental use cases only. The free pricing is its sole meaningful advantage.
Assessment date: March 14, 2026
Our methodology takes into account a range of factors including pricing, functionality, capabilities, benchmark performance, and real-world applicability. Rankings are reviewed and updated regularly as new models are released. Issues with our rankings? Contact us
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, including structured outputs and function calling.
Capabilities
Architecture
| Modality | Text + Image → Text |
| Tokenizer | Gemini |
| Instruct Type | gemma |
| Parameters | 4B |
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Evaluations
Benchmark data from Artificial Analysis and Hugging Face
Model Information
Live Performance
Live endpoint metrics — refreshed every 30 minutes.
