gemma
2B parameters
Commercial OK
Multimodal

Gemma 4 E2B (Effective 2B)

Smallest Gemma 4. Designed for phones and Raspberry-Pi-class hardware.

License: Gemma Terms of Use·Released Apr 2, 2026·Context: 131,072 tokens

Overview

Smallest Gemma 4. Designed for phones and Raspberry-Pi-class hardware.

Strengths

  • Phone-class footprint
  • Multimodal

Weaknesses

  • Limited reasoning

Quantization variants

Each quantization trades model quality for file size and VRAM. Q4_K_M is the most popular starting point.

QuantizationFile sizeVRAM required
Q4_K_M1.3 GB3 GB
Q8_02.2 GB4 GB

Get the model

Ollama

One-line install

ollama run gemma4:e2bRead our Ollama review →

HuggingFace

Original weights

huggingface.co/google/gemma-4-e2b-it

Source repository — direct quantization required.

Hardware that runs this

Cards with enough VRAM for at least one quantization of Gemma 4 E2B (Effective 2B).

Compare alternatives

Models worth comparing

Same parameter band, plus what's one tier above and below — so you can decide what actually fits your hardware.

Same tier
Models in the same parameter band as this one
Step up
More capable — bigger memory footprint
Step down
Smaller — faster, runs on weaker hardware
No verdicted models in the next tier down yet.

Frequently asked

What's the minimum VRAM to run Gemma 4 E2B (Effective 2B)?

3GB of VRAM is enough to run Gemma 4 E2B (Effective 2B) at the Q4_K_M quantization (file size 1.3 GB). Higher-quality quantizations need more.

Can I use Gemma 4 E2B (Effective 2B) commercially?

Yes — Gemma 4 E2B (Effective 2B) ships under the Gemma Terms of Use, which permits commercial use. Always read the license text before deployment.

What's the context length of Gemma 4 E2B (Effective 2B)?

Gemma 4 E2B (Effective 2B) supports a context window of 131,072 tokens (about 131K).

How do I install Gemma 4 E2B (Effective 2B) with Ollama?

Run `ollama pull gemma4:e2b` to download, then `ollama run gemma4:e2b` to start a chat session. The default quantization is Q4_K_M.

Does Gemma 4 E2B (Effective 2B) support images?

Yes — Gemma 4 E2B (Effective 2B) is multimodal and accepts text + vision inputs. Vision support requires a runner that handles its image-conditioning architecture.

Source: huggingface.co/google/gemma-4-e2b-it

Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.