GPUs tracked45Price history8 dayssince Sep 3, 2026Price points (24h)7,968 pointsBiggest 24h dropBiggest 24h riseData updated

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 Tesla V100 16GB, at about $659.

VRAM needed for each Gemma version

AmazonJP
4 versions
VersionReleasedContext
Gemma 4 E4BDense8BMar 2, 2026128K7Tesla V100 16GB$659 · 16 GB
Gemma 4 12BDense12BMay 23, 2026256K11Tesla V100 16GB$659 · 16 GB
Gemma 4 26B A4BMoE25.8B (4B active)Mar 11, 2026256K6plus 13 GB of RAMTesla V100 16GB$659 · 16 GB · Experts offloaded
Gemma 4 31BDense31.3BMar 11, 2026256K26Tesla V100 32GB$1,141 · 32 GB

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 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. New official releases are scanned weekly; architecture parameters and sourced or estimated weight sizes are reviewed before publication.

VendorGoogle DeepMind
LicenseApache-2.0
Hugging Face orggoogle