CanItRun Logocanitrun.

Gemma 4 E4B

Gemma 4 E4B needs roughly 3.9 GB VRAM at Q4_K_M quantization (10.1 GB at FP16). 103 GPUs we track can run it fully in VRAM at 8k context.

103 GPUs run this natively · 1 with CPU offload

Google4B params125k contextApache 2.0Commercial use ok

Gemma 4 E4B is a 4B parameter dense model developed by Google. April 2026, part of Google's 'elastic' Gemma line — the E4B/E2B naming continues the convention Google introduced with Gemma 3n, where the number denotes effective parameters under the MatFormer nested-model technique rather than raw parameter count. Text, vision, and audio inputs at 128K context, Apache 2.0.

To run Gemma 4 E4B locally: Q5_K_M needs roughly 3GB — runs comfortably on 8GB GPUs with room for the vision/audio encoders and context.

MMLU-Pro 69.4 at a 4B footprint is strong for the size class, consistent with the quality-density gains Gemma 3n demonstrated at launch.

VRAM at each quantization

Figures below assume 8k context; KV cache grows linearly as context length increases.

QuantWeightsKV cacheTotal
FP3216.0 GB1.01 GB19.1 GB
BF168.0 GB1.01 GB10.1 GB
FP168.0 GB1.01 GB10.1 GB
Q8_04.3 GB1.01 GB5.9 GB
Q6_K3.3 GB1.01 GB4.8 GB
Q5_K_Mrec2.9 GB1.01 GB4.3 GB
Q4_K_M2.4 GB1.01 GB3.9 GB
Q3_K_M1.9 GB1.01 GB3.3 GB
Q2_K1.5 GB1.01 GB2.8 GB
NVFP4cuda2.0 GB1.01 GB3.4 GB

KV cache is calculated at 8k context (FP16). Note that NVFP4 only runs on CUDA GPUs. Turn on TurboQuant in the calculator above for lower KV cache estimates.

Benchmarks

MMLU-Pro
69.4

GPUs that run Gemma 4 E4B natively (103)

Plus 1 GPUs that run it with CPU offload (slower)
Hugging Face ↗Ollama ↗Released 2026-04-02

Explore

Browse all guides →Browse all models →Browse all GPUs →

Frequently asked questions

What are the VRAM requirements for Gemma 4 E4B?
Gemma 4 E4B requires approximately 3.9 GB of VRAM at Q4_K_M quantization, 5.9 GB at Q8, and 10.1 GB at FP16. These numbers assume 8k context window; VRAM scales linearly with context length due to the KV cache.
How many parameters does Gemma 4 E4B have?
Gemma 4 E4B has 4 billion parameters.
How capable is Gemma 4 E4B?
With an MMLU-Pro score of 69.4, Gemma 4 E4B delivers solid general-purpose performance suitable for most everyday tasks and professional use.
Can Gemma 4 E4B run on a 16 GB GPU?
Yes. Gemma 4 E4B needs 3.9 GB at Q4_K_M, which fits in a 16 GB GPU like the RTX 4080 or RTX 4070 Ti Super.
What is the smallest quantization for Gemma 4 E4B that fits in 24 GB of VRAM?
At FP32, Gemma 4 E4B needs 19.0 GB — the highest-quality quantization that fits in 24 GB of VRAM.
What GPU do I need to run Gemma 4 E4B locally?
A 16 GB GPU is enough. At Q4_K_M, Gemma 4 E4B needs 3.9 GB VRAM. Good options: RTX 4080 (16 GB), RTX 4070 Ti Super (16 GB).