Gemma4 is a locally installable Ollama model from the Gemma series. Agent Mag tracks its local install command, available tags, modalities, and runtime details on this page.

How do you use Gemma4?

Gemma4 can be installed locally with npx agentmag add model gemma4, which wraps ollama pull gemma4. This page also includes local Ollama run and API examples.

Gemma4 is listed as a local Ollama model. There is no hosted token price in Agent Mag; local compute and storage requirements depend on the tag you pull.

Gemma4

All models

GoogleGemmaLocal runtimeFree

Gemma4

256K context

Ollama install

29 tags

Gemma4 is available through Ollama for local agent workflows, with support for text, image input. 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.

What is Gemma4?

Gemma4 is a local model entry from Ollama that Agent Mag tracks for install commands, available tags, modalities, and agent workflow fit. Builders can install it with the Agent Mag CLI and run it through Ollama on their own machine.

Agent Mag install

Ollama model ID

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.

Modalities

Input

textimage

Output

text

Ollama Tags

Tag	Size	Context	Input
gemma4:latest	9.6GB	128K	text, image
gemma4:e2b	7.2GB	128K	text, image
gemma4:e4b	9.6GB	128K	text, image
gemma4:26b	18GB	256K	text, image
gemma4:31b	20GB	256K	text, image
gemma4:31b-cloud	-	256K	text, image