European open-weight model family known for efficiency at small parameter counts.
| Critère | Mistral | Phi |
|---|---|---|
| Context window | 32k tokens | 128k tokens |
| License | Apache-2.0 | MIT |
| Open weights | Yes | Yes |
| Parameters | 7B | 3.8B, 14B |
| Provider | Mistral AI | Microsoft |
Les lignes grisées sont identiques pour les deux ; ce sont les lignes qui diffèrent qui motivent la recommandation ci-dessous.
Généré à partir des différences ci-dessus par des règles structurées, et non par un modèle.
model · Models
Mistral is an open-weight model family that emphasises quality per parameter rather than raw size, so a small model can run on modest hardware without collapsing in quality. It solves the cost problem for teams whose workload is not hard enough to justify a frontier model. It exists because most production tasks are narrow enough that a well-trained small model is sufficient, and serving one is an order of magnitude cheaper than calling a large hosted model.
model · Models
Phi is a family of small language models trained on a deliberately narrow, high-quality corpus of textbooks and exercises rather than on a web-scale crawl. It solves the assumption that capability requires scale, showing that data selection can substitute for a large part of it. It exists because it reframes the question from how much data to what kind of data, and the answer is useful when the budget is a single GPU.
