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.

Appstokens
Hermes Agent11,32 Bn
Zazen (Freebuff fork)3,16 Bn
Cline2,56 Bn
Kilo Code2,44 Bn
pi1,59 Bn
OpenClaw1,05 Bn
Codex938,81 Md
DeepSeek Harness847,26 Md
Portkey AI639,39 Md
HighLevel375,1 Md
ISEKAI ZERO364,56 Md
Framer348,63 Md
Hello Minds, powered by Ethoswarm316,97 Md
ZCode279,83 Md
Descript253,44 Md