Skip to content

Qwen 2.5 32B

Apache 2.0

Alibaba · 32B · transformer-decoder

2024-09-19131K context32B params

Use Cases

chatcodereasoningmultilingualtoolsmathwritingsummary

Quantization Options

QuantBitsVRAMQualityStatus
Q4_K_Mrec420.7 GBGood
Q5_K_M523.9 GBGood
Q8_0834.0 GBExcellent

About this model

Qwen 2.5 32B is a powerful model from Alibaba that delivers excellent performance across reasoning, coding, and multilingual tasks. With 32 billion parameters, it occupies a sweet spot between efficiency and capability that makes it highly popular for local deployment. The model supports 128K context, tool use, and structured output generation. At Q4 quantization, it fits on a single high-end consumer GPU, offering near-70B-class performance at a fraction of the resource cost.

Benchmarks

83.3
mmlu