AI ranking
Local AI — agentic
Open-weights and local models (Qwen, DeepSeek, Gemma, Llama, Phi, Mistral… 35B or fewer) suited to agentic use: models present in both chat and code. These are models usable inside agentic systems, not applications or scaffolds.
Top visuel
- 01 Qwen3.8 27B 84.97
- 02 Qwen3.5 27B 81.80
- 03 Qwen3.5 35B A3b 76.71
- 04 Qwen3.6 27B 66.58
- 05 QwQ 32B 44.64
- 06 Gemma 3 27B It 42.05
- 07 Falcon H1r 7B 34.91
- 08 Qwen2.5 Coder 32B Instruct 33.57
- 09 Phi 3 mini instruct 3.8b 18.90
Models beyond roughly 35 billion parameters are not ranked in the local categories. Le Recul favours models that can genuinely be run locally, without heavy professional infrastructure.
Compare models. Cochez jusqu'à 3 modèles dans le tableau ci-dessous, puis lancez la comparaison : qui gagne sur quel usage, de combien, et avec quelle solidité.
| # | Model | Vendor | Score | Assessment | |
|---|---|---|---|---|---|
| 01 | Alibaba | 84.97 / 100 | Partial | ||
| 02 | Alibaba | 81.80 / 100 | Reliable | ||
| 03 | Alibaba | 76.71 / 100 | Reliable | ||
| 04 | Alibaba | 66.58 / 100 | Reliable | ||
| 05 | Alibaba | 44.64 / 100 | Reliable | ||
| 06 | 42.05 / 100 | Reliable | |||
| 07 | Falcon H1r 7B | Tii uae | 34.91 / 100 | Reliable | |
| 08 | Alibaba | 33.57 / 100 | Reliable | ||
| 09 | Microsoft | 18.90 / 100 | Reliable |
Score indicatif, pondéré à partir de sources publiques. Méthodologie transparente. Voir la page Classement IA pour la méthodologie complète et les autres catégories.