Quantization publisher

csoares31

csoares31 publishes 3 quantizations across 1 models in our index, averaging 9.796 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
1
Quantizations
3
Models covered
1
Avg effective bpw
9.796
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuantcsoares31vsTheirsDifference
AMALIA-9B-0626-DPOQ4_K_M5.20 GiBduarteocarmo5.20 GiB0.0%
AMALIA-9B-0626-DPOQ8_09.06 GiBduarteocarmo9.06 GiB0.0%
AMALIA-9B-0626-DPOQ4_K_M5.20 GiBlayerx-labs5.20 GiB-0.0%
AMALIA-9B-0626-DPOQ8_09.06 GiBlayerx-labs9.06 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
AMALIA-9B-0626-DPO35.20 GiB