ig1
/

Qwen2.5-VL-32B-Instruct-FP8-Dynamic

Image-Text-to-Text

text-generation-inference

compressed-tensors

Model card Files Files and versions

FP8 activation quantization performed with llm-compressor

Downloads last month: 17

Safetensors

Model size

33.5B params

Tensor type

BF16

·

F8_E4M3

·

Model tree for ig1/Qwen2.5-VL-32B-Instruct-FP8-Dynamic

Base model

Qwen/Qwen2.5-VL-32B-Instruct

Quantized

(25)

this model