Quantization publisher

ash2813

ash2813 publishes 2 quantizations across 1 models in our index, averaging 10.682 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
2
Models covered
1
Avg effective bpw
10.682
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuantash2813vsTheirsDifference
llm-jp-4-32b-a3b-thinkingQ4_K_M20.04 GiBmmnga-o19.93 GiB+0.6%
llm-jp-4-32b-a3b-thinkingQ4_K_M20.04 GiBhiratagoh19.93 GiB+0.6%

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

ModelQuantizationsSmallest
llm-jp-4-32b-a3b-thinking220.04 GiB