exllamav3 quantizations of ArliAI's QwQ-32B-ArliAI-RpR-v4.
2.25bpw h6 (10.201 GiB)
3.00bpw h6 (12.925 GiB)
4.00bpw h6 (16.558 GiB)
6.00bpw h6 (23.824 GiB)
8.00bpw h8 (31.271 GiB)
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support