Skip to content

Qwen 2.5 72B

Qwen License

Alibaba · 72B · transformer-decoder

2024-09-19131K context72B params

Use Cases

chatcodereasoningmultilingualtoolsmathwritingsummary

Quantization Options

QuantBitsVRAMQualityStatus
Q4_K_Mrec444.7 GBGood
Q5_K_M551.9 GBGood
Q8_0874.0 GBExcellent

About this model

Qwen 2.5 72B is the flagship model of the Qwen 2.5 series, delivering frontier-class performance on reasoning, coding, math, and multilingual benchmarks. It competes directly with the best open models at the 70B scale from Meta and others. This model requires multi-GPU setups for comfortable inference but rewards users with exceptional output quality. It supports 128K context, advanced tool use, and performs strongly across 29+ languages with particular excellence in Chinese and English.

Benchmarks

85.3
mmlu