FitMyLLM
Google/Dense

GoogleGemma 3n E4B

Gemma 3n E4B — mobile-friendly model with vision and multilingual support.

chatcodingmultilingualvision
8B
Parameters
32K
Context length
22
Benchmarks
6
Quantizations
200K
HF downloads
Architecture
Dense
Released
2025-06-25
Layers
34
KV Heads
4
Head Dim
256
Family
gemma

Quantization Options

Context length:
QuantBitsVRAM @ 16KQuality
Q4_K_M4.89
5.7 GB
5.4 + 0.3 KV
good
Q5_K_S5.57
6.4 GB
6.1 + 0.3 KV
good
Q5_K_M5.7
6.5 GB
6.2 + 0.3 KV
good
Q6_K6.56
7.4 GB
7.0 + 0.3 KV
excellent
Q8_08.5
9.3 GB
9.0 + 0.3 KV
lossless
FP1616
16.8 GB
16.5 + 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 E4B now

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

Community Ratings

Loading ratings...

Benchmarks (22)

Run this model

Easiest way to get started·Beginners
Docs ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run gemma3n:e4b-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 C2070
6 GB VRAM • 143 GB/s
NVIDIA
NVIDIA Tesla C2075
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla C2090
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla M2070
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla M2070-Q
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla M2075
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla M2090
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla X2070
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla X2090
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla K20X
6 GB VRAM • 250 GB/s
NVIDIA
NVIDIA Tesla K20Xm
6 GB VRAM • 250 GB/s
NVIDIA

Find the best GPU for Gemma 3n E4B

Build Hardware for Gemma 3n E4B

Gemma 3n E4B — mobile-friendly model with vision and multilingual support.

Spec sheet

Gemma 3n E4B — 8B Dense.

Specifications
Parameters
8B
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_M4.895.4 GB94%
Q5_K_S5.576.1 GB96%
Q5_K_M5.76.2 GB96%
Q6_K6.567.0 GB97%
Q8_08.59.0 GB100%
FP161616.5 GB100%
Benchmark scores
HumanEval75.0
MMLU-PRO50.6
MATH23.2
IFEval73.8
BBH52.9
GPQA14.2
MUSR15.0
MBPP63.6
Arena Elo1440
GPQA Diamond29.6
LiveCodeBench14.6
AIME14.3
MATH-50077.1
HLE4.4
AA Intelligence6.4
AA Coding4.2
AA Math14.3
IFBench27.9
Terminal-Bench Hard2.3
τ²-Bench5.0
SciCode8.1
Terminal-Bench 2.10.7
Run command

Run Gemma 3n E4B locally with Ollama — needs 5.4 GB VRAM at Q4_K_M:

$ollama run gemma3n:e4b
Compatible GPUs
30 @ Q4_K_M