Gemma 3 12B — Specifications
| Desarrollador | Google |
|---|
| Tipo | LLM (multimodal) |
|---|
| Modalidad | Text, Image → Text |
|---|
| Parámetros | 12B |
|---|
| Ventana de contexto | 128K |
|---|
| Salida máxima | — |
|---|
| Licencia | Gemma (open) |
|---|
| Pesos abiertos | ✅ Yes |
|---|
| Fecha de lanzamiento | 2025 |
|---|
| Input price | $0.05 /1M |
|---|
| Output price | $0.15 /1M |
|---|
| API providers | Google AI Studio, OpenRouter, Ollama |
|---|
🖥️ Run it locally
| VRAM (4-bit) | ~8 GB |
|---|
| Minimum GPU | RTX 4070 12GB |
|---|
Official page →
A mid-size multimodal Gemma 3 (text + image, 128K, 140+ languages) that runs 4-bit on a 12GB GPU — a great balance of capability and footprint.
