Quantization publisher

migtissera

migtissera publishes 7 quantizations across 2 models in our index, averaging 7.767 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
2
Quantizations
7
Models covered
2
Avg effective bpw
7.767
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuantmigtisseravsTheirsDifference
Tess-4-27BQ8_029.58 GiBbartowski27.12 GiB+9.1%
Tess-4-27BQ6_K20.57 GiBbartowski21.85 GiB-5.9%
Tess-4-27BQ4_K_M17.30 GiBbartowski16.55 GiB+4.5%
Tess-4-9BQ6_K6.85 GiBbartowski7.30 GiB-6.1%
Tess-4-9BQ4_K_M5.24 GiBbartowski5.63 GiB-6.9%
Tess-4-9BQ8_08.87 GiBbartowski9.13 GiB-2.8%

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
Tess-4-27B317.30 GiB
Tess-4-9B45.24 GiB