gemma

4B parameters

Commercial OK

Multimodal

Gemma 4 E4B (Effective 4B)

Edge-class Gemma 4. The 'Effective 4B' branding signals it punches above its parameter count via training-data quality.

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

Overview

Edge-class Gemma 4. The 'Effective 4B' branding signals it punches above its parameter count via training-data quality.

Strengths

Edge-class
Multimodal at 4B

Weaknesses

Reasoning ceiling lower than larger Gemma 4

Quantization variants

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

Quantization	File size	VRAM required
Q4_K_M	2.5 GB	4 GB
Q8_0	4.4 GB	6 GB

Get the model

Ollama

One-line install

ollama run gemma4:e4bRead our Ollama review →

HuggingFace

Original weights

huggingface.co/google/gemma-4-e4b-it

Source repository — direct quantization required.

Hardware that runs this

Cards with enough VRAM for at least one quantization of Gemma 4 E4B (Effective 4B).

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

Llama 3.2 1B Instruct
llama · 1B
6.0/10

Frequently asked

What's the minimum VRAM to run Gemma 4 E4B (Effective 4B)?

4GB of VRAM is enough to run Gemma 4 E4B (Effective 4B) at the Q4_K_M quantization (file size 2.5 GB). Higher-quality quantizations need more.

Can I use Gemma 4 E4B (Effective 4B) commercially?

Yes — Gemma 4 E4B (Effective 4B) 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 E4B (Effective 4B)?

Gemma 4 E4B (Effective 4B) supports a context window of 131,072 tokens (about 131K).

How do I install Gemma 4 E4B (Effective 4B) with Ollama?

Run `ollama pull gemma4:e4b` to download, then `ollama run gemma4:e4b` to start a chat session. The default quantization is Q4_K_M.

Does Gemma 4 E4B (Effective 4B) support images?

Yes — Gemma 4 E4B (Effective 4B) is multimodal and accepts text + vision inputs. Vision support requires a runner that handles its image-conditioning architecture.

Source: huggingface.co/google/gemma-4-e4b-it

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