Gemma 3 4Bon Krater.ai

Gemma 3 introduces multimodality, supporting vision-language input and text outputs.

Released March 13, 2025

Specifications

Gemma 3 4B at a glance

Context

131.1K tokens

Max output

16.4K tokens

Input

Text, Image

Output

Text

Input price

$0.05 / 1M

Output price

$0.10 / 1M

Knowledge cutoff

2024-08-31

Image inputStructured outputs

Capabilities

What it is good at

Catalog capabilities

  • Accepts image input
  • Generates text responses
  • Supports structured outputs
  • Instruction format: gemma

Good for

Image understandingLong documentsStructured responses

Benchmarks

Catalog data, not Krater benchmarks.

Coding index score

2.7

FAQ

Questions about Gemma 3 4B

Clear answers based on the model catalog and Krater access.

Gemma 3 4B supports a context window of 131,072 tokens.

Use Gemma 3 4B in your API

Connect with Krater's unified API.

API access

Ready to use Gemma 3 4B?

Access leading models in one focused workspace.