GLM-4.7-Flash-FP8

This is a DeepSeekV3-style FP8 checkpoint of zai-org/GLM-4.7-Flash made for the purpose of debugging inference code locally.

Downloads last month
93
Safetensors
Model size
31B params
Tensor type
F32
BF16
F8_E4M3
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support

Model tree for Doctor-Shotgun/GLM-4.7-Flash-FP8

Quantized
(78)
this model