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...
Modalidades
Texto
Preço in / out
₩ 123 / ₩ 491
1M
Contexto
262,14 mil
Lançado
31 de jul. de 2025
Apps
Apps que mais utilizam este modelo.
| Apps | tokens |
|---|---|
| Hermes Agent | 11,32 tri |
| Zazen (Freebuff fork) | 3,16 tri |
| Cline | 2,56 tri |
| Kilo Code | 2,44 tri |
| pi | 1,59 tri |
| OpenClaw | 1,05 tri |
| Codex | 938,81 bi |
| DeepSeek Harness | 847,26 bi |
| Portkey AI | 639,39 bi |
| HighLevel | 375,1 bi |
| ISEKAI ZERO | 364,56 bi |
| Framer | 348,63 bi |
| Hello Minds, powered by Ethoswarm | 316,97 bi |
| ZCode | 279,83 bi |
| Descript | 253,44 bi |