Quantization publisher

Reza2kn

Reza2kn publishes 11 quantizations across 1 models in our index, averaging 5.749 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
1
Quantizations
11
Models covered
1
Avg effective bpw
5.749
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuantReza2knvsTheirsDifference
Qianfan-OCRQ2_K1.68 GiBDevQuasar1.68 GiB-0.0%
Qianfan-OCRQ3_K_M2.09 GiBDevQuasar2.09 GiB-0.0%
Qianfan-OCRQ4_K_M2.54 GiBDevQuasar2.54 GiB-0.0%
Qianfan-OCRQ5_K_M2.95 GiBDevQuasar2.95 GiB-0.0%
Qianfan-OCRQ6_K3.38 GiBDevQuasar3.38 GiB-0.0%
Qianfan-OCRQ8_04.38 GiBDevQuasar4.38 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
Qianfan-OCR111.68 GiB