Qwen2 72B
Alibaba·
LLMsopen-weightWorkstation
Overview
First non-Western top-tier open model. Demonstrated that frontier-class open-weight models could come from outside the US/EU ecosystem.
Capabilities and innovations
0.5B / 1.5B / 7B / 72B parameters128K context window29 languages supportedStrong math and codingYARN-based context extensionDual-chunk attentionMultilingual data curation pipeline
Benchmarks
| Benchmark | Score | Source |
|---|---|---|
| GPQA Diamond | 37.9% | unsourced |
| MMLU | 84.2% | unsourced |
Architecture and hardware
- Parameters
- 72B total (Dense)
- Estimated VRAM at Q4
- ~42 GB, Workstation class
- Quantization formats
- GGUF, GPTQ, AWQ
- Recommended runtime
- Ollama
- License
- Apache 2.0
Links
More from Alibaba
Data curated by AI Model Timeline. See the methodology for admission criteria, benchmark eras and source priority.