Qwen3-Coder-30B-A3B-Instruct Open-source
By Qwen
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...
HF trending
12
Community signal
Rank over time
Lower is better. Trend lines from each ranking source where this model has appeared.
Score over time
ELO from Arena, quality index from Artificial Analysis, or token-share % from OpenRouter.