Quantization publisher

0xSero

0xSero publishes 3 quantizations across 1 models in our index, averaging 6.648 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 2 of the pairs we can compare — the same label does not mean the same file.

From the file· summed file bytes
Repositories
1
Quantizations
3
Models covered
1
Avg effective bpw
6.648
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuant0xSerovsTheirsDifference
Qwen3.5-99BQ4_K_M56.06 GiBRobinsonLabs56.06 GiB-0.0%
Qwen3.5-99BQ6_K75.74 GiBRobinsonLabs75.74 GiB-0.0%

A quantization label describes a target, not a recipe. Publishers make different choices about which tensors to keep at higher precision, and some apply an importance matrix while others don't — so two files both honestly labelled the same thing can differ measurably in size and in quality.

Models they publish

ModelQuantizationsSmallest
Qwen3.5-99B356.06 GiB