asi992h
/

Qwen2.5-VL-7B-Instruct-FP4

Image-Text-to-Text

text-generation-inference

4-bit precision

Model card Files Files and versions

Qwen2.5-VL-7B-Instruct-FP4

FP4 quant of Qwen/Qwen2.5-VL-7B-Instruct suitable for fast, low-loss use on Blackwell GPUs.

Downloads last month: 35

Safetensors

Model size

4.8B params

Tensor type

F32

·

F16

·

U8

·

Model tree for asi992h/Qwen2.5-VL-7B-Instruct-FP4

Base model

Qwen/Qwen2.5-VL-7B-Instruct

Quantized

(94)

this model