ArtusDev
/

Qwen3-32b_8bitgs128_hqq

Text Generation

8-bit precision

Model card Files Files and versions

This is an HQQ all 8-bit (group-size=128) quantized Qwen3-32B model.

Downloads last month: 92

Safetensors

Model size

33.2B params

Tensor type

FP16

·

I64

·

U8

·

Inference Providers NEW

Text Generation

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for ArtusDev/Qwen3-32b_8bitgs128_hqq

Base model

Qwen/Qwen3-32B

Quantized

(88)

this model

Collection including ArtusDev/Qwen3-32b_8bitgs128_hqq

Qwen_Qwen3 - 32B - HQQ

Quants by ArtusDev • 3 items • Updated 7 days ago