A July 2025 instruction-tuned refresh of Qwen3 30B-A3B, Alibaba's efficient MoE model, with improved instruction following for general chat and task completion at low cost.
Cost rate
0.1x
Context
262K
Released
Jul 29, 2025
Input
Text
Output
Text
Support
ReasoningTool callingStructured outputs
Performance
Median latency and throughput measured across recent requests.
Throughput84 tok/s
Latency0.35s
Best at
The categories where this model ranks highest.
Business, Management, & Finance
#173 · top 42%
Software & IT Services
#178 · top 42%
Mathematical
#178 · top 44%
Medicine & Healthcare
#190 · top 48%
| Domain | Score | Rank |
|---|---|---|
| Software & IT Services | 1428 | #178 |
| Writing, Literature, & Language | 1341 | #214 |
| Life, Physical, & Social Science | 1395 | #195 |
| Entertainment, Sports, & Media | 1331 | #203 |
| Business, Management, & Finance | 1397 | #173 |
| Mathematical | 1399 | #178 |
| Legal & Government | 1384 | #196 |
| Medicine & Healthcare | 1400 | #190 |
Latest news about Qwen3 30B A3B Instruct 2507
Recent articles and community posts, linked to their original sources.
Mapping every neuron in Qwen3-8BHacker News302- Qwen3-Coder writes less secure code when told it's for a US personaHacker News243118
- 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