Google·3 sizes·General LLM
Gemma 3 models: sizes & hardware to run them
The Gemma 3 family spans 3 sizes from 4B to 27B. Each size maps to a different hardware tier — below is the approximate memory each needs at 4-bit and the device we’d start with for a private local deployment.
VisionMultilingualLong context
Sizes & hardware
| Model | Params | Context | ~VRAM @ 4-bit | Minimum device | Recommended |
|---|---|---|---|---|---|
| Gemma 3 4B | 4B | 128K | ~3GB | NVIDIA GeForce RTX 3060 12GB | NVIDIA B200 (placeholder) |
| Gemma 3 12B | 12B | 128K | ~8GB | NVIDIA GeForce RTX 3060 12GB | NVIDIA B200 (placeholder) |
| Gemma 3 27B | 27B | 128K | ~17GB | NVIDIA GeForce RTX 3090 | NVIDIA B200 (placeholder) |
Memory figures are approximate working-set estimates (weights + KV cache at modest context); treat as ±. Device picks come from our compatibility engine, best on-prem fit first.
Open each size
General LLM
Gemma 3 4B
8GB GPUs, a Mac mini, or a small mini PC at 4-bit. A current small generalist with a long context and image input.
General LLM
Gemma 3 12B
16GB+ GPUs at 4-bit. A current mid-size generalist with long context and image input.
General LLM
Gemma 3 27B
A 24GB card (RTX 3090/4090) or 32GB+ Mac at 4-bit. The flagship Gemma 3 with long context and vision.
Run Gemma 3 models inside a private AI Business OS
Run your own AI agents on hardware you control — private by design, no per-seat data leaving your premises. BrainOutput helps you pick the right machine and turn it into a working AI Business OS.
Explore the AI Business OS