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
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support