EXL3 quantization of Qwen3.6-35B-A3B-StyleTune, 6 bits per weight.

Use CPU offloading by setting EXL3_MOE_CPU_OFFLOAD.

E.g. with TabbyAPI:

EXL3_MOE_CPU_OFFLOAD=10 python main.py ...
Downloads last month
22
Safetensors
Model size
14B params
Tensor type
BF16
F16
I16
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support

Model tree for isogen/Qwen3.6-35B-A3B-StyleTune-exl3-6bpw

Quantized
(6)
this model