Gemma Models — Hardware Requirements

11 Gemma models from Google and the community, from the smallest that runs in 0.1 GB of VRAM up to 27.0B parameters. Every row links to full quantization tables and GPU compatibility.

All Gemma Models by Size

ModelParamsContext
Functiongemma 270M IT268M
Functiongemma 270M Ft Mobile Actions270M
T5gemma B B Ul2 IT591M
Vaultgemma 1B1.0B
T5gemma L L Ul2 IT1.2B
Gemma 7B8.5B
Gemma 7B IT8.5B
Codegemma 7B IT8.5B
Turkish Gemma 9B T19.2B8K
Turkish Gemma 9B v0.19.2B8K
Medgemma 27B Text IT27.0B

How Gemma Compares — Benchmark Rating

Gemma 7B is the highest-rated Gemma model with an overall benchmark rating of 51.3/100 — #31 among 73 open models. The top proprietary model, Claude Fable 5 Max, scores 89.9. Click a model to see its full benchmark breakdown.

Claude Fable 5 Max · proprietary89.9
GPT 5.5 · proprietary89.2
GPT 5.6 Sol · proprietary89.2
Claude Fable 5 · proprietary88.6
Claude Opus 4.8 · proprietary88.1
Composite of normalized public benchmark scores (methodology) · Gemma · other models

Frequently Asked Questions

How much VRAM do I need to run a Gemma model?
The smallest Gemma model, Functiongemma 270M IT, runs from 0.1 GB of VRAM at an aggressive quantization. Larger family members need proportionally more — see the table above for every model.
Which Gemma models can I run on a 16 GB GPU?
11 of 11 Gemma models fit in 16 GB of VRAM at some quantization, including Functiongemma 270M IT, Medgemma 27B Text IT, Gemma 7B.
What is the most popular Gemma model to run locally?
Functiongemma 270M IT is the most downloaded Gemma model in local-friendly quantized formats. It runs from 0.1 GB of VRAM.
How do Gemma models score on benchmarks?
Gemma 7B leads the family with an overall benchmark rating of 51.3/100, ranking #31 among 73 open models, while the top proprietary model, Claude Fable 5 Max, scores 89.9. See the comparison chart above for the full standings.