Hugging Face's logo

Qwen
/
Qwen1.5-32B-Chat-AWQ

Text Generation
Transformers
Safetensors
English
qwen2
chat
conversational
text-generation-inference
4-bit precision
awq
Model card Files Community
2

推理速度比14B-AWQ慢很多,是否正常

#1
by william0014 - opened
Discussion
william0014

同样内容的回复, 14B-AWQ 为 6秒, 32B-AWQ为20秒.

Your need to confirm your account before you can post a new comment.

Sign up or log in to comment