Magnitude
Google logo

Gemma 4 E2B

by Google · Released · Apache 2.0

Very small dense model with per-layer embeddings optimized for on-device use.

Parameters
5.1B dense
Context
128K tokens
Input
Text + image
Speculative decoding
Not yet
Intelligence
14%
License
Apache 2.0
Variants
Q4 QAT
Source
Hugging Face ↗

Downloads

Sizes include the vision projector Magnitude installs. Every file is pinned to an immutable Hugging Face commit.

Variant Format Download Fidelity
Q4 QAT UD-Q4_K_XLQAT 3.6 GB 58/100

How it compares

Intelligence across every model in the catalog: each model's Artificial Analysis Intelligence Index score as a percentage of the top model on v4.3.2, as of Sep 29, 2026.

  1. Qwen3.8 27B 59%
  2. Gemma 4 31B 33%
  3. Qwen3.6 35B-A3B 32%
  4. Muse Glimmer 30B 30%
  5. Gemma 4 26B-A4B 29%
  6. Gemma 4 12B 25%
  7. Qwen3.5 4B 23%
  8. MiniCPM5 2B 22%
  9. Nemotron 3.5 Lightning 30B-A3B 22%
  10. Qwen3.5 9B 19%
  11. Gemma 4 E4B 15%
  12. Liquid LFM2.5 2.6B 15%
  13. MiniCPM5 1B 15%
  14. Gemma 4 E2B 14%
  15. Liquid LFM2.5 8B-A1B 13%

Works with your agent

One click in Magnitude connects Gemma 4 E2B to any of these harnesses.

  • Pi
  • OpenCode
  • Hermes
  • OpenClaw
  • Codex
  • Claude Code
  • Oh My Pi
  • Cline

Related models

FAQ

How much memory does Gemma 4 E2B need?

The smallest download is 3.6 GB. Plan for the weights plus a few gigabytes for context. Magnitude measures your free memory and only recommends variants that fit with room to work.

Can I run Gemma 4 E2B on a Mac?

Yes. Magnitude runs GGUF models on Apple Silicon through Metal, and on NVIDIA, AMD, and CPU-only machines on Windows and Linux. The app estimates tokens per second for your exact chip before you download.

Which variant should I pick?

Magnitude picks for you: the highest-fidelity variant that fits your memory. If you choose manually, Q4 QAT keeps the most fidelity.

Catalog data from magnitudedev/magnitude, updated Sep 29, 2026.

Run Gemma 4 E2B on your machine

Other platforms