FitMyLLM
Google/Dense

GoogleGemma 3n E2B

Gemma 3n E2B — Google's efficient model designed for phones and edge devices.

chatcodingmultilingualvision
5.44B
Parameters
32K
Context length
19
Benchmarks
6
Quantizations
100K
HF downloads
Architecture
Dense
Released
2025-06-25
Layers
26
KV Heads
4
Head Dim
256
Family
gemma

Quantization Options

Context length:
QuantBitsVRAM @ 16KQuality
Q4_K_M4.89
4.1 GB
3.8 + 0.3 KV
good
Q5_K_S5.57
4.5 GB
4.3 + 0.3 KV
good
Q5_K_M5.7
4.6 GB
4.4 + 0.3 KV
good
Q6_K6.56
5.2 GB
4.9 + 0.3 KV
excellent
Q8_08.5
6.5 GB
6.3 + 0.3 KV
lossless
FP1616
11.6 GB
11.4 + 0.3 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 3n E2B now

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

Community Ratings

Loading ratings...

Benchmarks (19)

Run this model

Easiest way to get started·Beginners
Docs ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run gemma3n: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 3n E2B

Build Hardware for Gemma 3n E2B

Gemma 3n E2B — Google's efficient model designed for phones and edge devices.

Spec sheet

Gemma 3n E2B — 5.44B Dense.

Specifications
Parameters
5.44B
Architecture
Dense Transformer
Context Length
32K tokens
Capabilities
chat, coding, multilingual, vision
Release Date
2025-06-25
Provider
Google
Family
gemma
VRAM requirements
QuantBPWVRAMQuality
Q4_K_M4.893.8 GB94%
Q5_K_S5.574.3 GB96%
Q5_K_M5.74.4 GB96%
Q6_K6.564.9 GB97%
Q8_08.56.3 GB100%
FP161611.4 GB100%
Benchmark scores
HumanEval66.5
MMLU-PRO17.6
MATH6.2
IFEval40.3
BBH44.3
GPQA4.0
MUSR14.9
MBPP56.6
GPQA Diamond22.9
LiveCodeBench9.5
AIME10.3
MATH-50069.1
HLE4.0
AA Intelligence4.8
AA Coding2.2
AA Math10.3
IFBench22.0
Terminal-Bench Hard0.8
SciCode5.2
Run command

Run Gemma 3n E2B locally with Ollama — needs 3.8 GB VRAM at Q4_K_M:

$ollama run gemma3n:e2b
Compatible GPUs
30 @ Q4_K_M