Agent Mag
SUBSCRIBE
Gemma 3 4B
All models
GoogleGoogleGemma

Gemma 3 4B

131K context$0.040/M input$0.080/M output

Gemma 3 4B is an AI model from Google built for agent workflows, with support for text, image input and text output. 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,...

What is Gemma 3 4B?

Gemma 3 4B is an AI model from Google that Agent Mag tracks for pricing, context window, modalities, benchmarks, and API compatibility. Builders can use this page to compare Gemma 3 4B against other models for agent workflows and production deployments.

Model ID

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,...

Modalities
Input
textimage
Output
text
Supported Parameters
frequency_penaltymax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstoptemperaturetop_ktop_p

More from Google

Gemma 4 26B A4B
262K ctx$0.060/M

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

Gemma 4 31B (free)
262K ctxFree

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...

Gemma 4 31B
262K ctx$0.130/M

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...

Gemma 4 26B A4B (free)
262K ctxFree

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

Related content

Browse the AI models directory

Compare pricing, local installs, context windows, and modality filters across the full model catalog.

Explore AI agent tools

Find frameworks, SDKs, and infrastructure tools that pair with this model in production workflows.

Read Agent Mag model and agent articles

See Agent Mag coverage of model benchmarks, agent frameworks, and deployment patterns.