Mistral NeMo 12B — Specifications
| Developer | Mistral AI |
|---|---|
| Type | LLM (dense) |
| Modality | Text → Text |
| Parameters | 12B |
| Context window | 128K |
| Max output | — |
| License | Apache 2.0 (open) |
| Open weights | ✅ Yes |
| Released | 2024 |
| Input price | $0.02 /1M |
| Output price | $0.04 /1M |
| API providers | Mistral, OpenRouter, Ollama |
🖥️ Run it locally
| VRAM (4-bit) | ~7.5 GB |
|---|---|
| Minimum GPU | RTX 4070 12GB / RTX 3060 |
A 12B model built by Mistral AI with NVIDIA — Apache 2.0, 128K context, strong multilingual support. Runs 4-bit on a 12GB GPU.