Quantization publisher

Avesed

Avesed publishes 5 quantizations across 1 models in our index, averaging 5.772 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
5
Models covered
1
Avg effective bpw
5.772
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuantAvesedvsTheirsDifference
Qwopus3.6-27B-v2-abliteratedQ2_K10.12 GiBmradermacher10.12 GiB-0.0%
Qwopus3.6-27B-v2-abliteratedQ4_K_M15.66 GiBmradermacher15.66 GiB-0.0%
Qwopus3.6-27B-v2-abliteratedQ5_K_M18.19 GiBmradermacher18.19 GiB-0.0%
Qwopus3.6-27B-v2-abliteratedQ6_K20.89 GiBmradermacher20.89 GiB-0.0%
Qwopus3.6-27B-v2-abliteratedQ8_027.05 GiBmradermacher27.05 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
Qwopus3.6-27B-v2-abliterated510.12 GiB