FitMyLLM
Google/Dense

GoogleGemma 4 E2B

Gemma 4 E2B — 2.3B effective params from 5.1B total via Per-Layer Embeddings. Vision + audio, 128K context.

chatmultilingualvisionaudio
5.1B
Parameters
128K
Context length
14
Benchmarks
6
Quantizations
100K
HF downloads
Architecture
Dense
Released
2026-04-02
Layers
35
KV Heads
1
Head Dim
256
Family
gemma

Quantization Options

Context length:
QuantBitsVRAM @ 16KQuality
Q4_K_M4.89
3.7 GB
3.6 + 0.1 KV
good
Q5_K_S5.57
4.1 GB
4.0 + 0.1 KV
good
Q5_K_M5.7
4.2 GB
4.1 + 0.1 KV
good
Q6_K6.56
4.7 GB
4.7 + 0.1 KV
excellent
Q8_08.5
6.0 GB
5.9 + 0.1 KV
lossless
FP1616
10.8 GB
10.7 + 0.1 KV
lossless

Select your GPU above to see speed estimates and compatibility for each quantization.

Deploying for a team or in production? Size GPUs, cost & scaling in Enterprise →
Ready to run this?Rent by the hour

Rent a GPU and run Gemma 4 E2B now

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (14)

Run this model

Easiest way to get started·Beginners
Docs ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run gemma4:e2b-it-q4_K_M

Downloads and runs automatically. Add --verbose for speed stats.

Setup guide
>_

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more
Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

NVIDIA Tesla C1080
4 GB VRAM • 102 GB/s
NVIDIA
NVIDIA Tesla K10
4 GB VRAM • 160 GB/s
NVIDIA
NVIDIA Tesla M4
4 GB VRAM • 88 GB/s
NVIDIA
AMD Radeon Instinct MI8
4 GB VRAM • 512 GB/s
AMD
NVIDIA RTX A1000 Embedded
4 GB VRAM • 224 GB/s
NVIDIA
NVIDIA RTX A2000 Embedded
4 GB VRAM • 192 GB/s
NVIDIA

Find the best GPU for Gemma 4 E2B

Build Hardware for Gemma 4 E2B
Spec sheet

Gemma 4 E2B — 5.1B Dense.

Specifications
Parameters
5.1B
Architecture
Dense Transformer
Context Length
128K tokens
Capabilities
chat, multilingual, vision, audio
Release Date
2026-04-02
Provider
Google
Family
gemma
VRAM requirements
QuantBPWVRAMQuality
Q4_K_M4.893.6 GB94%
Q5_K_S5.574.0 GB96%
Q5_K_M5.74.1 GB96%
Q6_K6.564.7 GB97%
Q8_08.55.9 GB100%
FP161610.7 GB100%
Benchmark scores
MMLU-PRO60.0
BBH21.9
GPQA Diamond43.4
HLE4.8
AA Intelligence15.2
AA Coding9.0
LiveCodeBench44.0
AIME37.5
IFBench38.0
Terminal-Bench Hard3.0
τ²-Bench20.8
SciCode20.9
AA Long Context15.0
Terminal-Bench 2.10.4
Run command

Run Gemma 4 E2B locally with Ollama — needs 3.6 GB VRAM at Q4_K_M:

$ollama run gemma4:e2b
Compatible GPUs
30 @ Q4_K_M