Side-by-side comparison of Mistral Small (Mistral AI · France) and Qwen 2.5 (Alibaba · China) for self-hosted deployment of the open-weight model. Mistral Small is rated EU-ready; Qwen 2.5 is conditional. They part ways on training data: Mistral Small is "Partial", Qwen 2.5 is "Undisclosed".
| Field | ||
|---|---|---|
| Summary | ||
| Verdict | EU-ready Best-in-class permissive licence from an EU vendor. Apache 2.0 means no usage caps, no royalty, no revocation risk. | Conditional Legally clean under Apache 2.0, but Chinese origin raises supply-chain and geopolitical questions. Vet carefully for sensitive use cases. |
| Last reviewed | 2026-04-15 | 2026-04-15 |
| Open-weight | ||
| Licence | Apache 2.0 | Apache 2.0 |
| Commercial use | Yes | Yes |
| Training data | Partial | Undisclosed |
| Origin | EU | China |
| Performance & pricing? | ||
| Quality index | 13/100 | 16/100 |
| Speed | 152 tok/s | 55 tok/s |
| Blended price | $0.15/M | — |
| Context window | — | — |
| Evidence | ||
| Sources | ||
No overlapping sources between the two entries.