SalonbusAI
/

GLM-4-32B-0414-FP8

Model card Files Files and versions Community

FP8 Quantized Version of THUDM/GLM-4-32B-0414

Downloads last month: 204

Safetensors

Model size

32.6B params

Tensor type

BF16

·

F8_E4M3

·

Inference Providers NEW

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

Model tree for SalonbusAI/GLM-4-32B-0414-FP8

Base model

THUDM/GLM-4-32B-0414

Quantized

(28)

this model