Quantization publisher

layerx-labs

layerx-labs publishes 4 quantizations across 1 models in our index, averaging 8.510 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 6 of the pairs we can compare — the same label does not mean the same file.

From the file· summed file bytes
Repositories
1
Quantizations
4
Models covered
1
Avg effective bpw
8.510
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuantlayerx-labsvsTheirsDifference
AMALIA-9B-0626-DPOQ4_K_S4.96 GiBduarteocarmo4.96 GiB0.0%
AMALIA-9B-0626-DPOBF1617.05 GiBduarteocarmo17.05 GiB0.0%
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 GiBcsoares315.20 GiB0.0%
AMALIA-9B-0626-DPOQ8_09.06 GiBcsoares319.06 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
AMALIA-9B-0626-DPO44.96 GiB