Gemma 3 is Google's efficient open model family with the best quality-to-size ratio in its class. Available in 4B, 12B, and 27B sizes, these models punch above their weight on reasoning and instruction following.
Deploy Gemma 3 in minutes
Starting at $0.51/hr on dedicated GPU
| Model | GPU | VRAM | Price | Action |
|---|---|---|---|---|
Gemma 3 4B Small (4B) | L4 | 24 GB | $0.51/hr | Deploy |
Gemma 3 12B Medium (12B, Recommended) | L4 | 24 GB | $0.51/hr | Deploy |
Gemma 3 27B Large (27B) | RTX A6000 | 48 GB | $0.64/hr | Deploy |
Prices include 30% service fee. Billed per minute while running.
Pick your GPU and have it running in minutes. No infrastructure setup required.