Gemma 4 E4B

Released
2026-03-31
Last refreshed
2026-06-15
Status
Researched 208d ago
Open sourceCommercial use: permittedMultimodalRAGAgentsLong contextVisionJSON / Tool use
Google DeepMind releases · 54 in the last 12 months · this family litChangelog →
Specifications
Family
Gemma 4
Released
2026-03-31
Context
128K
Parameters
4B
Knowledge cutoff
2025-01
Openness
Open source
License
Apache 2.0OSI-approvedPermitted
Weights
Available
Code
Unknown
Created by

Pioneering artificial intelligence research.

London, United Kingdom
Founded 2014
Website
Pricing
Output / 1M
Free
Input / 1M
Free

Cheapest of 1 route · GCP Vertex AI

Providers(1)

About

Efficient 4B model with native audio input support. Balances performance and efficiency for edge and on-device deployment with reasoning and coding capabilities.

Providers(1)

Compare API pricing across 1 tracked provider route for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
GCP Vertex AIFreeFree
Serverless

Available via routers & gateways(13)

Capabilities

MultimodalJSON / Tool use

Benchmark peer barsfor RAG

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

Compare Gemma 4 E4B with other models