Gemma 2 Models — Hardware Requirements

15 Gemma 2 models from Google and the community, from the smallest that runs in 0.9 GB of VRAM up to 27.2B parameters. Every row links to full quantization tables and GPU compatibility.

All Gemma 2 Models by Size

ModelParamsContext
Gemma 2B IT2.5B
Gemma 2B2.5B
Codegemma 2B2.5B
Nidum Gemma 2B Uncensored2.5B8K
Gemma 2 2B IT2.6B8K
Gemma 2 2B2.6B
Gemma 2 2B Jpn IT2.6B
Txgemma 2B Predict2.6B
Shieldgemma 2B2.6B
T5gemma 2B 2B Ul25.6B
Text2cypher Gemma 2 9B IT Finetuned 2024v19B
Gemma 2 9B IT9.2B8K
Gemma 2 9B9.2B
Gemma 2 Mitra E9.2B8K
Gemma 2 27B IT27.2B8K

How Gemma 2 Compares — Benchmark Rating

Gemma 2 27B IT is the highest-rated Gemma 2 model with an overall benchmark rating of 32.5/100 — #63 among 75 open models. The top proprietary model, GPT 5.5, scores 88.8. Click a model to see its full benchmark breakdown.

GPT 5.5 · proprietary88.8
Claude Opus 4.7 · proprietary87.6
Claude Fable 5 · proprietary86.6
GPT 5.4 · proprietary86.6
Claude Opus 4.8 · proprietary84.4
Composite of normalized public benchmark scores (methodology) · Gemma 2 · other models

Frequently Asked Questions

How much VRAM do I need to run a Gemma 2 model?
The smallest Gemma 2 model, Gemma 2 2B IT, runs from 0.9 GB of VRAM at an aggressive quantization. Larger family members need proportionally more — see the table above for every model.
Which Gemma 2 models can I run on a 16 GB GPU?
15 of 15 Gemma 2 models fit in 16 GB of VRAM at some quantization, including Gemma 2 2B IT, Gemma 2 9B IT, Gemma 2 27B IT.
What is the most popular Gemma 2 model to run locally?
Gemma 2 2B IT is the most downloaded Gemma 2 model in local-friendly quantized formats. It runs from 0.9 GB of VRAM.
How do Gemma 2 models score on benchmarks?
Gemma 2 27B IT leads the family with an overall benchmark rating of 32.5/100, ranking #63 among 75 open models, while the top proprietary model, GPT 5.5, scores 88.8. See the comparison chart above for the full standings.