exllamav2 quantizations of ArliAI's QwQ-32B-ArliAI-RpR-v4.
2.25bpw h6 (10.213 GiB)
3.00bpw h6 (12.938 GiB)
4.00bpw h6 (16.571 GiB)
6.00bpw h6 (23.837 GiB)
8.00bpw h8 (31.254 GiB)
measurement.json
exllamav2 quantizations of ArliAI's QwQ-32B-ArliAI-RpR-v4.
2.25bpw h6 (10.213 GiB)
3.00bpw h6 (12.938 GiB)
4.00bpw h6 (16.571 GiB)
6.00bpw h6 (23.837 GiB)
8.00bpw h8 (31.254 GiB)
measurement.json