NEW Browse AI tools across categories — updated daily. See what's new →

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
Context window
160K tokens
Input price
$0.070 / 1M tok
Output price
$0.27 / 1M tok
Modalities
text
External ID
Qwen/Qwen3-Coder-30B-A3B-Instruct

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.

Back to all rankings