Qwen2.5-72B-Instruct
Alibaba's instruction-tuned flagship open-source model
Qwen2.5-72B-Instruct
Qwen • September 2024
Training Data
Up to mid 2024
Qwen2.5-72B-Instruct
September 2024
Parameters
72 billion
Training Method
Instruction Tuning
Context Window
128,000 tokens
Knowledge Cutoff
August 2024
Key Features
Open Source • Instruction Following • Long Context • Multilingual
Capabilities
Reasoning: Excellent
Instruction Following: Outstanding
Coding: Very Good
What's New in This Version
Open-source model competitive with proprietary alternatives
Alibaba's instruction-tuned flagship open-source model
What's New in This Version
Open-source model competitive with proprietary alternatives
Technical Specifications
Key Features
Capabilities
Other Qwen Models
Explore more models from Qwen
Qwen3.7-Max
Alibaba's closed text flagship for reasoning and long-horizon agents — 1M context, MCP and multi-agent orchestration, tuned for autonomous coding and office automation
Qwen3.7-Plus
Multimodal agent sibling to Qwen3.7-Max, adding native vision while keeping the 1M-token context and agentic tooling at a lower price point
Qwen3.6-27B
Alibaba's first dense open-weight Qwen3.6 — 27B beats 397B MoE on agentic coding via hybrid Gated DeltaNet + Gated Attention
