Qwen 2.5 72B Instruct AWQ
Qwen2.5 72B Instruct is a chat model developed by Qwen, capable of processing up to 32,768 tokens and handling streaming and structured output. It is licensed under an open-source license, allowing for flexibility in its use and modification.
Input
Output
Context
33K
Max Output
8K
Parameters
73B
Technical Specifications
Model TypeChat
Context Window32,768 tokens
Max Output Tokens8,192 tokens
Parameters73B
Release DateSep 17, 2024
Training CutoffJun 30, 2024
Licenseother
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
4.2%
HLE
16.0%
AIME
49.1%
GPQA
26.7%
SciCode
85.8%
MATH 500
72.0%
MMLU Pro
14.0
Math
11.9
Coding
27.6%
LiveCodeBench
9.6
Intelligence
Resources & Links
Estimated GPU Requirements for Qwen 2.5 72B Instruct AWQ
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 24, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.