Gemma 3 27B — Specifications
| Développeur | Google |
|---|
| Type | LLM (multimodal) |
|---|
| Modalité | Text, Image → Text |
|---|
| Paramètres | 27B |
|---|
| Fenêtre de contexte | 128K |
|---|
| Sortie maximale | — |
|---|
| Licence | Gemma (open) |
|---|
| Poids ouverts | ✅ Yes |
|---|
| Date de sortie | 2025 |
|---|
| Input price | $0.08 /1M |
|---|
| Output price | $0.16 /1M |
|---|
| API providers | Google AI Studio, OpenRouter, Ollama |
|---|
🖥️ Run it locally
| VRAM (4-bit) | ~16 GB |
|---|
| Minimum GPU | RTX 4080 16GB / RTX 4090 |
|---|
Official page →
Google’s largest open Gemma 3 — multimodal (text + image), 128K context, 140+ languages. The strongest single-GPU local model in its class; runs 4-bit on a 16–24GB card.
