Mistral 7B — Specifications
| Developer | Mistral AI |
|---|---|
| Type | LLM (dense) |
| Modality | Text → Text |
| Parameters | 7B |
| Context window | 32K |
| Max output | — |
| License | Apache 2.0 (open) |
| Open weights | ✅ Yes |
| Released | 2023 |
| Input price | $0.02 /1M |
| Output price | $0.03 /1M |
| API providers | Mistral, DeepInfra, OpenRouter, Ollama |
🖥️ Run it locally
| VRAM (4-bit) | ~4.5 GB |
|---|---|
| Minimum GPU | Any 6GB GPU |
The model that kicked off the open-LLM wave — 7B, Apache 2.0, tiny footprint. Still a solid, ultra-cheap baseline that runs on a 6GB GPU at 4-bit.