Quantization publisher

DevQuasar-11

DevQuasar-11 publishes 7 quantizations across 1 models in our index, averaging 4.224 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 5 of the pairs we can compare — the same label does not mean the same file.

From the file· summed file bytes
Repositories
1
Quantizations
7
Models covered
1
Avg effective bpw
4.224
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuantDevQuasar-11vsTheirsDifference
cogito-671b-v2.1Q2_K227.38 GiBunsloth228.82 GiB-0.6%
cogito-671b-v2.1Q3_K_M297.34 GiBunsloth298.44 GiB-0.4%
cogito-671b-v2.1Q4_K_M376.71 GiBunsloth377.55 GiB-0.2%
cogito-671b-v2.1Q5_K_M442.77 GiBunsloth443.46 GiB-0.2%
cogito-671b-v2.1Q8_0664.29 GiBunsloth664.29 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
cogito-671b-v2.17138.82 GiB