Hugging Face's logo

Qwen
/
Qwen2-VL-2B-Instruct-GPTQ-Int8

Image-Text-to-Text
Safetensors
English
qwen2_vl
multimodal
conversational
8-bit precision
gptq
Model card Files Community
3
New discussion

inference time and memory consumption on quantized model
#3 opened about 1 month ago by
DILLIP-KUMAR