Qwen: Qwen3 Coder 30B A3B Instruct
qwen/qwen3-coder-30b-a3b-instruct
Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...
Modalités
Texte
Prix entrée / sortie
123 ₩ / 491 ₩
1M
Contexte
262,14 k
Publié
31 juil. 2025
Apps
Applications utilisant le plus ce modèle.
| Apps | tokens |
|---|---|
| Hermes Agent | 11,32 Bn |
| Zazen (Freebuff fork) | 3,16 Bn |
| Cline | 2,56 Bn |
| Kilo Code | 2,44 Bn |
| pi | 1,59 Bn |
| OpenClaw | 1,05 Bn |
| Codex | 938,81 Md |
| DeepSeek Harness | 847,26 Md |
| Portkey AI | 639,39 Md |
| HighLevel | 375,1 Md |
| ISEKAI ZERO | 364,56 Md |
| Framer | 348,63 Md |
| Hello Minds, powered by Ethoswarm | 316,97 Md |
| ZCode | 279,83 Md |
| Descript | 253,44 Md |