gemma4

open-weight31B

Gemma 4 models are designed to deliver frontier-level performance at each size. They are well-suited for reasoning, agentic workflows, coding, and multimodal understanding.

Context
131K

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Infrastructure
Streaming
Fine-tuning

Details

Provider Ollama
Creator Google AI
Family—
Licenseopen-weight
Status—
Typechat
Input modalitiestext, image
Output modalitiestext
Open weightYes
Parameters31B
Architecture—
Context window131K tokens
Max input—
Max output—
Reasoning tokensYes
Knowledge cutoff—
Release date
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

API

GET/v1/models/ollama/gemma4

gemma4

Gemma 4 models are designed to deliver frontier-level performance at each size. They are well-suited for reasoning, agentic workflows, coding, and multimodal understanding.

Changes · 3 entries
gemma4update82e6976Apr 7, 2026, 02:37 PM
capabilitiesreasoningyes
parameters26→31
release_date2026-04-02
reasoning_tokensyes
gemma4updatefdb701fApr 5, 2026, 05:48 AM
parameters26
gemma4createc2a7935Apr 4, 2026, 01:05 AM