switch-base-128_qmoe

This is the google/switch-base-128 model quantized with the QMoE framework to ternary precision and stored in the custom further compressed QMoE format.

Please see the QMoE repository for how to use this model.

Downloads last month
5
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Space using ISTA-DASLab/switch-base-128_qmoe 1