Quantization publisher

sroecker

sroecker publishes 1 quantizations across 1 models in our index, averaging 5.644 effective bits per weight.

From the file· summed file bytes
Repositories
1
Quantizations
1
Models covered
1
Avg effective bpw
5.644
across their files

Models they publish

ModelQuantizationsSmallest
Qwen3.6-35B-REAP-Pruned-ratio-0.5112.48 GiB