Entity · model

Qwen2-72B

modelactiveqwen2-72b-c16fb0d7·1 events·first seen May 18, 2026

Aliases: Qwen2-72B

Co-occurring entities

Qwen2.5 Qwen2-57B-A14B Qwen1.5 Alibaba Qwen Team

More like this (12)

Qwen1.5-72B Qwen2-57B-A14B Qwen3-235B Qwen-7B Qwen2.5-VL-72B Qwen1.5-32B Qwen 2.5-7B Qwen1.5-110B Qwen3-30B-A3B Qwen3-4B Qwen2.5-VL Qwen3.6-27B

Recent events (1)

8Qwen Research·May 18, 2026·source ↗

Qwen2 Model Family Released: Five Sizes, 128K Context, Multilingual

Alibaba's Qwen team has released Qwen2, an evolution from Qwen1.5, comprising five pretrained and instruction-tuned models ranging from 0.5B to 72B parameters, including a 57B mixture-of-experts variant (57B-A14B). The release highlights training on 27 additional languages beyond English and Chinese, significantly improved coding and mathematics performance, and extended context support up to 128K tokens for the 7B and 72B instruct variants. Benchmark results are claimed to be state-of-the-art across a large number of evaluations.

Long Context Evolution Frontier Model Releases Qwen2-72B Qwen2.5 Qwen2-57B-A14B +4 more