qwertyuiopasdfg
/

glm4-32B-4bit

4-bit precision

Model card Files Files and versions

bnb-4bits Quantized Version of THUDM/GLM-4-32B-0414

Downloads last month: -

Safetensors

Model size

34B params

Tensor type

F32

·

BF16

·

U8

·

Inference Providers NEW

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