Quantization publisher

DevQuasar-5

DevQuasar-5 publishes 12 quantizations across 2 models in our index, averaging 5.554 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 2 of the pairs we can compare — the same label does not mean the same file.

From the file· summed file bytes
Repositories
2
Quantizations
12
Models covered
2
Avg effective bpw
5.554
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuantDevQuasar-5vsTheirsDifference
Qwen2.5-72B-Instruct-abliteratedQ2_K27.76 GiBmradermacher27.76 GiB-0.0%
Qwen2.5-72B-Instruct-abliteratedQ3_K_M35.11 GiBmradermacher35.11 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