Qwen2.5-72B-Instruct
Flagship 72B instruction-tuned model of Alibaba's Qwen2.5 series.
About
Qwen2.5-72B-Instruct is the largest instruction-tuned model in Alibaba's Qwen2.5 family, released in September 2024. With 72.7 billion parameters across 80 layers, it supports a 128K token context window and multilingual generation in more than 29 languages, with marked gains in coding, mathematics, and structured output over Qwen2.
The model is distributed under the Apache 2.0 license and became one of the most widely deployed open-weight chat models of its generation, serving as the base for countless fine-tunes, quantizations, and enterprise deployments.
Specs
Context window
Pricing
Free quota
API access
Weights
Released
Benchmarks
Provider-reported unless a source says otherwise. Benchmarks are marketing-adjacent by nature — treat them as directional.
Use cases
Trust score — 9/10
Scored 9/10 (verified tier, metrics-v1). Evidence: Verified via vendor site/docs/GitHub and reputable coverage, wave 131; Trending score 88/100 from researcher assessment.