924 2 weeks ago

Gemma 4 E4B (Google DeepMind) with thinking mode disabled. Compact multimodal model — 4.5B effective / 8B total parameters. Supports text, image and audio input. Designed for edge devices and local deployment. Knowledge cutoff: January 2025.

vision tools thinking audio
ollama run bjoernb/gemma4-e4b-fast

Applications

Claude Code
Claude Code ollama launch claude --model bjoernb/gemma4-e4b-fast
Codex
Codex ollama launch codex --model bjoernb/gemma4-e4b-fast
OpenCode
OpenCode ollama launch opencode --model bjoernb/gemma4-e4b-fast
OpenClaw
OpenClaw ollama launch openclaw --model bjoernb/gemma4-e4b-fast
Hermes Agent
Hermes Agent ollama launch hermes --model bjoernb/gemma4-e4b-fast

Models

View all →

Readme

No readme