Quantization publisher

tepirale

tepirale publishes 15 quantizations across 2 models in our index, averaging 8.544 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
3
Quantizations
15
Models covered
2
Avg effective bpw
8.544
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuanttepiralevsTheirsDifference
Ornith-Agents-A1-3.6-35B-A3B-dare_tiesQ4_K_M20.55 GiBTivaphraen19.71 GiB+4.2%
Ornith-Agents-A1-3.6-35B-A3B-dare_tiesQ5_K_M23.87 GiBTivaphraen23.03 GiB+3.6%
Ornith-Agents-A1-3.6-35B-A3B-dare_tiesQ4_K_M20.55 GiBTivaphraen19.71 GiB+4.2%
Ornith-Agents-A1-3.6-35B-A3B-dare_tiesQ5_K_M23.87 GiBTivaphraen23.03 GiB+3.6%

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