EXL3 quantization of Phi-4-mini-reasoning, 8 bits per weight, including output layers.

Downloads last month
8
Safetensors
Model size
2.53B params
Tensor type
F16
·
I16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for isogen/Phi-4-mini-reasoning-exl3-8bpw-h8

Quantized
(33)
this model