Quantization publisher

sabafallah

sabafallah publishes 9 quantizations across 3 models in our index, averaging 8.710 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 7 of the pairs we can compare — the same label does not mean the same file.

From the file· summed file bytes
Repositories
3
Quantizations
9
Models covered
3
Avg effective bpw
8.710
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuantsabafallahvsTheirsDifference
DeepSeek-OCRQ8_02.91 GiBNexaAI2.90 GiB+0.3%
DeepSeek-OCRBF165.47 GiBNexaAI5.47 GiB+0.1%
Unlimited-OCRQ8_02.91 GiBDevQuasar2.91 GiB0.0%
Unlimited-OCRQ4_K_M1.82 GiBDevQuasar1.82 GiB0.0%
Unlimited-OCRQ8_02.91 GiBsahilchachra2.91 GiB-0.0%
Unlimited-OCRQ4_K_M1.82 GiBsahilchachra1.82 GiB-0.0%
Unlimited-OCRBF165.47 GiBsahilchachra5.47 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
Unlimited-OCR31.82 GiB
DeepSeek-OCR-231.82 GiB
DeepSeek-OCR31.82 GiB