EXL3 models
Collection
16 items
•
Updated
•
15
EXL3 quants of Qwen3-0.6B
2.75 bits per weight / H5 *
3.00 bits per weight *
3.50 bits per weight
4.00 bits per weight
5.00 bits per weight
6.00 bits per weight
8.00 bits per weight / H8
*) Reasoning seems unstable below 3.5 bpw
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support