Google: Gemma 3 27B
Google: Gemma 3 27B is a text-and-image model with a 131,072-token context window and support for tool use. It does not include a built-in reasoning mode, and structured output support is unconfirmed. The 16,384-token output cap is adequate for most generation tasks but may constrain very long-form work. At $0.08 per million input tokens and $0.16 per million output tokens, this sits at the budget end of the multimodal market. That pricing is its clearest argument for consideration, but the benchmark picture is thin: a blended score of 19.9 drawn from only three benchmarks leaves capability claims largely unproven relative to more thoroughly evaluated competitors. Teams running high-volume, cost-sensitive workloads that include image inputs may find it worth piloting, but those prioritizing demonstrated performance across a broad task range should treat the benchmarks here as preliminary rather than conclusive.
- Model ID
- google/gemma-3-27b-it
- Vendor
- Tokenizer
- Gemini
- Input Modalities
- text, image
- Output Modalities
- text
- Max Output
- 16,384 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- not supported
- Vision
- ✓ accepts images
- Audio
- no
- Moderated
- no