Qwen

/

Qwen2.5-72B-Instruct-GPTQ-Int8

like 7

Follow

Qwen 3,263

Can we get this benchmark update for Qwen 2.5 ? https://qwen.readthedocs.io/en/latest/benchmark/quantization_benchmark.html

Or any one tested Qwen2.5 72B Int 8 vs Qwen2.5 32B ？ These two models have the same GPU resources ,but we want a better one.
Any suggestions ?