AI Model Timeline

Tracking the accelerating release frequency of frontier AI models.

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

BenchmarkScoreSource
GPQA Diamond37.9%unsourced
MMLU84.2%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.