Quantization publisher

pupsipups

pupsipups publishes 10 quantizations across 1 models in our index, averaging 5.218 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 1 of the pairs we can compare — the same label does not mean the same file.

From the file· summed file bytes
Repositories
1
Quantizations
10
Models covered
1
Avg effective bpw
5.218
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuantpupsipupsvsTheirsDifference
Qwen3.6-27B-Heretic2-Uncensored-Finetune-ThinkingQ6_K20.86 GiBBugTraceAI20.57 GiB+1.4%

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-Heretic2-Uncensored-Finetune-Thinking109.77 GiB