Quantization publisher

VlSav

VlSav publishes 2 quantizations across 1 models in our index, averaging 6.695 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
2
Quantizations
2
Models covered
1
Avg effective bpw
6.695
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuantVlSavvsTheirsDifference
Vikhr-Nemo-12B-Instruct-R-21-09-24Q8_012.13 GiBbartowski12.13 GiB-0.0%
Vikhr-Nemo-12B-Instruct-R-21-09-24Q4_K_M6.96 GiBbartowski6.96 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
Vikhr-Nemo-12B-Instruct-R-21-09-2426.96 GiB