Quantization publisher

deewu0809

deewu0809 publishes 5 quantizations across 1 models in our index, averaging 16.209 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
5
Models covered
1
Avg effective bpw
16.209
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuantdeewu0809vsTheirsDifference
Qwythos-9B-Claude-Mythos-5-1MQ5_K_M12.29 GiBwepiqx12.25 GiB+0.3%
Qwythos-9B-Claude-Mythos-5-1MQ4_K_M10.73 GiBempero-ai10.73 GiB0.0%
Qwythos-9B-Claude-Mythos-5-1MQ5_K_M12.29 GiBempero-ai12.29 GiB0.0%
Qwythos-9B-Claude-Mythos-5-1MQ6_K13.95 GiBempero-ai13.95 GiB0.0%
Qwythos-9B-Claude-Mythos-5-1MQ8_017.99 GiBempero-ai17.99 GiB0.0%
Qwythos-9B-Claude-Mythos-5-1MBF1633.83 GiBempero-ai33.83 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
Qwythos-9B-Claude-Mythos-5-1M510.73 GiB