Gemma 3 Models — Hardware Requirements
18 Gemma 3 models from Google and the community, from the smallest that runs in 0.1 GB of VRAM up to 27.4B parameters. Every row links to full quantization tables and GPU compatibility.
All Gemma 3 Models by Size
| Model | Params | Runs from | Context | Publisher | Quant downloads |
|---|---|---|---|---|---|
| Gemma 3 270M IT | 268M | 0.1 GB | — | ||
| Gemma 3 270M | 268M | 0.1 GB | — | ||
| Gemma 3 270M IT Heretic | 268M | 0.4 GB | 33K | ||
| Gemma 3 1B IT | 1000M | 0.3 GB | 33K | ||
| Gemma 3 1B Pt | 1000M | 0.3 GB | — | ||
| Gemma 3 1B IT Heretic Extreme Uncensored Abliterated | 1000M | 0.8 GB | 33K | ||
| Gemma3 1B CulturaViva ITA | 1000M | 0.8 GB | 33K | ||
| Gemma 3n E2B IT Litert Lm | 2B | 0.9 GB | — | ||
| Gemma 3 4B T1 IT | 3.9B | 2.3 GB | 131K | ||
| Gemma 3n E4B IT Litert Lm | 4B | 1.9 GB | — | ||
| Gemma 3 4B IT | 4.3B | 2.0 GB | — | ||
| Gemma 3n E2B IT | 5.4B | 1.6 GB | — | ||
| Gemma 3n E4B IT | 7.8B | 2.4 GB | — | ||
| Gemma 3 12B IT | 12.2B | 5.7 GB | 33K | ||
| Gemma 3 12B IT Heretic v2 | 12.2B | 6.2 GB | 131K | ||
| Gemma 3 12B IT Heretic | 12.2B | 6.2 GB | 131K | ||
| Gemma 3 27B IT | 27.4B | 12.8 GB | 131K |
How Gemma 3 Compares — Benchmark Rating
Gemma 3 27B IT is the highest-rated Gemma 3 model with an overall benchmark rating of 34.5/100 — #57 among 78 open models. The top proprietary model, Claude Fable 5 (high), scores 87.8. Click a model to see its full benchmark breakdown.
Claude Fable 5 (high) · proprietary87.8
Claude Opus 4.7 · proprietary86.4
Claude Fable 5 Max · proprietary82.4
GPT 6 Astra (high) · proprietary82.4
GPT 6 Astra Max · proprietary82.4
Kimi K366.8
GLM 565.9
DeepSeek R1 052863.1
Gemma 3 27B IT34.5
Gemma 3 12B IT24.5
Gemma 3 4B IT16.7
Frequently Asked Questions
- How much VRAM do I need to run a Gemma 3 model?
- The smallest Gemma 3 model, Gemma 3 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 3 models can I run on a 16 GB GPU?
- 17 of 17 Gemma 3 models fit in 16 GB of VRAM at some quantization, including Gemma 3 1B IT, Gemma 3 4B IT, Gemma 3 12B IT.
- What is the most popular Gemma 3 model to run locally?
- Gemma 3 1B IT is the most downloaded Gemma 3 model in local-friendly quantized formats. It runs from 0.3 GB of VRAM.
- How do Gemma 3 models score on benchmarks?
- Gemma 3 27B IT leads the family with an overall benchmark rating of 34.5/100, ranking #57 among 78 open models, while the top proprietary model, Claude Fable 5 (high), scores 87.8. See the comparison chart above for the full standings.