GPUs tracked39Price history3 dayssince Sep 3, 2026Price points (24h)11,753 pointsBiggest 24h dropBiggest 24h riseData updated Sep 5, 2026

What Do You Need to Run Gemma Locally? VRAM by Version

Gemma currently has 4 versions you can deploy locally. The smallest, Gemma 4 E4B, needs 7GB of VRAM at Q4; the largest, Gemma 4 31B, needs 26GB. The cheapest device that gets one running is the GeForce RTX 2080 Ti, with no used-price data yet.

VRAM needed for each Gemma version

4 versions
VersionReleasedContext
Gemma 4 E4BDense8BMar 2, 2026128K7GeForce RTX 2080 Ti · 11 GB4,850,749
Gemma 4 12BDense12BMay 23, 2026256K11GeForce RTX 2080 Ti · 11 GB3,195,490
Gemma 4 26B A4BMoE25.8B (4B active)Mar 11, 2026256K6plus 13 GB of RAMRadeon RX 7900 XT · 20 GB8,211,474
Gemma 4 31BDense31.3BMar 11, 2026256K26Arc Pro B65 · 32 GB8,332,852

Minimum VRAM = Q4_K_M weights + KV cache for an 8K context + 1GB runtime overhead, rounded up. The cheapest device is the first one that fits when sorting by median used price on the current price basis.

About Gemma

Gemma is published by Google DeepMind under Apache-2.0. This page covers 4 versions ranging from 8B to 31.3B parameters; structure parameters and quantized sizes are synced weekly from Hugging Face.

VendorGoogle DeepMind
LicenseApache-2.0
Hugging Face orggoogle