Quantization publisher

inflatebot

inflatebot publishes 4 quantizations across 1 models in our index, averaging 8.991 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 7 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
8.991
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuantinflatebotvsTheirsDifference
MN-12B-Mag-Mell-R1Q6_K9.37 GiBmradermacher9.37 GiB-0.0%
MN-12B-Mag-Mell-R1Q4_K_M6.96 GiBmradermacher6.96 GiB-0.0%
MN-12B-Mag-Mell-R1Q8_012.13 GiBmradermacher12.13 GiB-0.0%
MN-12B-Mag-Mell-R1Q4_K_M6.96 GiBbartowski6.96 GiB-0.0%
MN-12B-Mag-Mell-R1Q8_012.13 GiBbartowski12.13 GiB-0.0%
MN-12B-Mag-Mell-R1Q6_K9.37 GiBbartowski9.37 GiB-0.0%
MN-12B-Mag-Mell-R1F1622.82 GiBbartowski22.82 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
MN-12B-Mag-Mell-R146.96 GiB