A 30B-A3B mixture-of-experts version of Qwen3 Coder, Alibaba's agentic coding model, offering strong code generation and repository-scale understanding at lower inference cost than the full-size Coder model.
Cost rate
0.1x
Context
262K
Released
Jul 31, 2025
Input
Text
Output
Text
Support
ReasoningTool callingStructured outputs
Performance
Median latency and throughput measured across recent requests.
Throughput147 tok/s
Latency1.18s
Best at
The categories where this model ranks highest.
No top-ranked categories found.
| Category | Win rate | Rank |
|---|---|---|
| Data Visualization | 54.7% | #109 |
| UI Component | 54.1% | #120 |
| Website | 57.1% | #121 |
Latest news about Qwen3 Coder 30B A3B Instruct
Recent articles and community posts, linked to their original sources.
- Qwen3-Coder writes less secure code when told it's for a US personaHacker News243118
Mapping every neuron in Qwen3-8BHacker News302- Show HN: Qwen3-4B with the AI writing tics trained outHacker News158113
Doubling Qwen Flash Next speed with Strata HotRodNo place like localhost18,864
Qwen 4 Max is here! OpenAI and Anthropic are in troubleSimon Høiberg17,830
Qwen4 Max Just Dropped, China's New BEST AI Model!AI Revolution84,709