Quantization publisher

zeeksa

zeeksa publishes 5 quantizations across 1 models in our index, averaging 3.159 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 4 of the pairs we can compare — the same label does not mean the same file.

From the file· summed file bytes
Repositories
1
Quantizations
5
Models covered
1
Avg effective bpw
3.159
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuantzeeksavsTheirsDifference
Qwen3.6-27B-Uncensored-HauhauCS-AggressiveIQ2_M9.32 GiBAIOpsInSpace9.74 GiB-4.3%
Qwen3.6-27B-Uncensored-HauhauCS-AggressiveIQ3_M11.72 GiBAIOpsInSpace12.14 GiB-3.5%
Qwen3.6-27B-Uncensored-HauhauCS-AggressiveIQ3_XS11.15 GiBAIOpsInSpace11.57 GiB-3.6%
Qwen3.6-27B-Uncensored-HauhauCS-AggressiveIQ4_XS14.05 GiBAIOpsInSpace14.47 GiB-2.9%

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
Qwen3.6-27B-Uncensored-HauhauCS-Aggressive53.23 GiB