Qwen2
Alibaba·
LLMsopen-weightcloud + localWorkstation
Overview
Major upgrade with 72B flagship, competitive with leading Western models.
Capabilities and innovations
72B Parameters128k contextMultilingual (29 languages)GQA ArchitectureDual Chunk AttentionYARN Scaling
Benchmarks
| Benchmark | Score | Source |
|---|---|---|
| GPQA Diamond | 30.4% | unsourced |
| MMLU | 84.2% | unsourced |
- Humanity’s Last Exam (no tools): not reported by the vendor
- SWE-bench Verified: not reported by the vendor
- SWE-bench Pro: benchmark did not exist at release
- MMLU-Pro: benchmark did not exist at release
- Terminal-Bench 2.x: benchmark did not exist at release
- MMMU-Pro: benchmark did not exist at release
Architecture and hardware
- Parameters
- 72B total (Dense)
- Estimated VRAM at Q4
- ~42 GB, Workstation class
Links
More from Alibaba
Data curated by AI Model Timeline. See the methodology for admission criteria, benchmark eras and source priority.