Azaz666
/

Qwen2.5-VL-7B-Instruct-AWQ-INT4

vision-language-model

4-bit precision

Model card Files Files and versions

Qwen2.5-VL-7B-Instruct-AWQ-INT4 / quant_meta.json

Azaz666's picture

Upload AWQ-INT4 quantized model

7eca9f5 verified about 1 month ago

history blame contribute delete

197 Bytes

	{
	"model_id": "Qwen/Qwen2.5-VL-7B-Instruct",
	"family": "qwen25vl",
	"method": "awq",
	"w_bit": 4,
	"group_size": 128,
	"quant_time_s": 783.0,
	"calib_samples": 64,
	"calib_seq_len": 256
	}