BestLLMfor EN Your hardware. Your LLM. Your call.
APIOpen data Find my LLM
Model fiche

Gemma 3n E2B

By Google · United States

Updated 2026-07-13

chat general multilingual small
Parameters
2B
License
Gemma
Context
32k
VRAM (Q4)
2 GB
Released
May 2025

Overview

Google's Gemma 3n with 2B effective parameters (6B raw) using MatFormer, covering 140+ languages. Optimized for mobile and edge; text-only on Ollama.

When to pick this model

  • Mobile and embedded deployments where memory is scarce
  • Multilingual edge inference across 140+ languages
  • Battery-constrained on-device chat
  • MatFormer-based research and experimentation

VRAM requirements by quantization

VRAM REQUIRED (GB)Q4_K_M2 GBQ5_K_M2.5 GBQ8_03.5 GBFP166 GB
QuantizationVRAM required
Q4_K_M (recommended)2 GB
Q5_K_M2.5 GB
Q8_03.5 GB
FP16 (no quantization)6 GB

VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.

In practice, Gemma 3n E2B fits an 8 GB consumer card at Q4_K_M (2 GB). Stepping up to Q8_0 nearly doubles the footprint to 3.5 GB, and unquantized FP16 weights take 6 GB — plan your GPU around the Q4 or Q5 figure unless you specifically need the higher fidelity.

Without a GPU, Gemma 3n E2B needs roughly 6 GB of system RAM to run on CPU via llama.cpp or Ollama — workable for background jobs, but far slower than GPU inference. Throughput estimates from our compatibility engine: around 35 tokens/sec on entry-level GPUs, on the order of 100 tokens/sec on a mid-range card, and up to 200 tokens/sec on high-end hardware — assuming the chosen quantization fully fits in VRAM.

What hardware do you need

The table below matches Gemma 3n E2B to common GPU memory tiers, using the highest-fidelity quantization that fully fits each card class. Spilling layers to system RAM works but costs most of the speed, so size your card to the quantization you actually want to run.

GPU memoryExample cardsBest fit for Gemma 3n E2B
8 GBRTX 5070 Laptop, RTX 5060, RTX 5060 Ti 8GBFP16 (6 GB used)
12 GBRTX 5070, RTX 5070 Ti Laptop, RTX 4080 LaptopFP16 (6 GB used)
16 GBRTX 5080, RTX 4080 Super, Radeon RX 9070 XTFP16 (6 GB used)
24 GBRTX 4090, Radeon RX 7900 XTX, RTX 5090 LaptopFP16 (6 GB used)
32 GBRTX 5090FP16 (6 GB used)

Which GPU should you buy to run Gemma 3n E2B?

To run Gemma 3n E2B locally at Q4, you need ~2 GB of VRAM. The best value for this is a RTX 5060 (8 GB VRAM).

Check RTX 5060 price on Amazon →

As an Amazon Associate, BestLLMfor earns from qualifying purchases, at no extra cost to you. It does not influence our independent rankings.

Strengths

  • Built specifically for mobile and edge hardware
  • 140+ language coverage in a tiny footprint
  • MatFormer architecture maximizes memory efficiency
  • Per-layer shared embeddings cut RAM use

Limitations

  • 32k context only
  • Absolute quality trails Gemma 3 9B
  • Gemma license — not as permissive as Apache 2.0
  • Multimodal features not exposed via Ollama

Typical workloads

In our catalog grid, Gemma 3n E2B is filed under Mobile/Edge, Compact Multilingual — the use cases where its size/quality trade-off makes the most sense. Its tags translate to concrete workloads: multilingual workloads.

The 32k-token context window covers long chats and mid-sized documents, though very large retrieval workloads will need chunking. It ships under the Gemma license — commercial use is generally possible but read the specific terms before embedding it in a product.

Architecture & training

Architecture: Gemma 3n E2B · on-device architecture · 2B effective · matPow

Training: Google Gemma 3n, optimized for mobile/edge with shared per-layer embeddings.

Verdict

Google's most memory-efficient small model — purpose-built for mobile and edge inference, with multilingual to match.

Quick start

ollama run gemma3n:e2b

Or use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.

Similar models worth comparing

Frequently asked questions

How much VRAM does Gemma 3n E2B need?

At the recommended Q4_K_M quantization, Gemma 3n E2B needs about 2 GB of VRAM. Q8_0 takes 3.5 GB, and unquantized FP16 weights take 6 GB.

Can Gemma 3n E2B run without a GPU?

Yes — with roughly 6 GB of system RAM it runs CPU-only through llama.cpp or Ollama. Expect a fraction of GPU speed, which is fine for background or batch jobs but slow for interactive chat.

What context window does Gemma 3n E2B support?

Gemma 3n E2B supports a 32k-token context window (32,768 tokens).

Can I use Gemma 3n E2B commercially?

Gemma 3n E2B ships under the Gemma license. Commercial use is generally permitted subject to its terms — review the license text before shipping a product.

How fast is Gemma 3n E2B on consumer hardware?

Our compatibility engine estimates on the order of 100 tokens/sec on a mid-range GPU and up to 200 tokens/sec on high-end cards, assuming the quantization fully fits in VRAM.

Which quantization of Gemma 3n E2B should I download first?

Start with Q4_K_M (2 GB) — the standard size/quality sweet spot. Step up to Q5_K_M or Q8_0 only if you have VRAM headroom. It already fits an 8 GB card at FP16.

Tools

Is Gemma 3n E2B the right pick for you?

Compute self-hosted ROI → Back to catalog