Quantization publisher

Loverboy69

Loverboy69 publishes 23 quantizations across 1 models in our index, averaging 6.562 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
23
Models covered
1
Avg effective bpw
6.562
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuantLoverboy69vsTheirsDifference
Dolphin3.0-Qwen2.5-3bQ4_K_M1.80 GiBitlwas1.80 GiB0.0%

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
Dolphin3.0-Qwen2.5-3b231.06 GiB