Quantization publisher

poolside

poolside publishes 5 quantizations across 2 models in our index, averaging 10.432 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 8 of the pairs we can compare — the same label does not mean the same file.

From the file· summed file bytes
Repositories
2
Quantizations
5
Models covered
2
Avg effective bpw
10.432
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuantpoolsidevsTheirsDifference
Laguna-S-2.1Q4_K_M89.44 GiBlmstudio-community66.28 GiB+34.9%
Laguna-S-2.1Q4_K_M89.44 GiBbartowski66.83 GiB+33.8%
Laguna-S-2.1Q8_0119.91 GiBlmstudio-community116.44 GiB+3.0%
Laguna-S-2.1Q8_0119.91 GiBbartowski116.44 GiB+3.0%
Laguna-S-2.1Q8_0119.91 GiBunsloth116.44 GiB+3.0%
Laguna-XS-2.1Q4_K_M18.88 GiBbartowski19.14 GiB-1.3%
Laguna-XS-2.1BF1662.33 GiBbartowski62.33 GiB-0.0%
Laguna-XS-2.1Q4_K_M18.88 GiBlmstudio-community18.88 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
Laguna-XS-2.1218.88 GiB
Laguna-S-2.1389.44 GiB