Qwen: Qwen3 30B A3B Instruct 2507
qwen/qwen3-30b-a3b-instruct-2507
Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...
Modalidades
Texto
Precio entrada / salida
85 KRW / 339 KRW
1M
Contexto
262,14 mil
Lanzado
30 jul 2025
Apps
Apps que más utilizan este modelo.
| Apps | tokens |
|---|---|
| Hermes Agent | 11,32 B |
| Zazen (Freebuff fork) | 3,16 B |
| Cline | 2,56 B |
| Kilo Code | 2,44 B |
| pi | 1,59 B |
| OpenClaw | 1,05 B |
| Codex | 938,81 mil M |
| DeepSeek Harness | 847,26 mil M |
| Portkey AI | 639,39 mil M |
| HighLevel | 375,1 mil M |
| ISEKAI ZERO | 364,56 mil M |
| Framer | 348,63 mil M |
| Hello Minds, powered by Ethoswarm | 316,97 mil M |
| ZCode | 279,83 mil M |
| Descript | 253,44 mil M |