Quantization publisher

zetasepic

zetasepic publishes 7 quantizations across 1 models in our index, averaging 5.222 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 7 of the pairs we can compare — the same label does not mean the same file.

From the file· summed file bytes
Repositories
1
Quantizations
7
Models covered
1
Avg effective bpw
5.222
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuantzetasepicvsTheirsDifference
Qwen2.5-72BIQ4_XS37.40 GiBThomasBaruzier36.98 GiB+1.1%
Qwen2.5-72BQ2_K27.76 GiBThomasBaruzier27.76 GiB-0.0%
Qwen2.5-72BIQ3_M33.07 GiBThomasBaruzier33.07 GiB-0.0%
Qwen2.5-72BQ4_K_M44.16 GiBThomasBaruzier44.16 GiB-0.0%
Qwen2.5-72BQ6_K59.93 GiBThomasBaruzier59.93 GiB-0.0%
Qwen2.5-72BQ8_071.96 GiBThomasBaruzier71.96 GiB-0.0%
Qwen2.5-72BQ3_K_M35.11 GiBThomasBaruzier35.11 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
Qwen2.5-72B727.76 GiB