Quantization publisher

hudsongouge

hudsongouge publishes 12 quantizations across 1 models in our index, averaging 7.235 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 8 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
1
Avg effective bpw
7.235
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuanthudsongougevsTheirsDifference
MiniCPM5-1BQ5_K_M0.73 GiBAbiray0.73 GiB-0.0%
MiniCPM5-1BQ5_K_M0.73 GiBAbiray0.73 GiB-0.0%
MiniCPM5-1BF162.02 GiBAbiray2.02 GiB0.0%
MiniCPM5-1BQ8_01.07 GiBAbiray1.07 GiB0.0%
MiniCPM5-1BQ4_K_M0.64 GiBAbiray0.64 GiB0.0%
MiniCPM5-1BQ4_K_M0.64 GiBAbiray0.64 GiB-0.0%
MiniCPM5-1BQ8_01.07 GiBAbiray1.07 GiB-0.0%
MiniCPM5-1BF162.02 GiBAbiray2.02 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
MiniCPM5-1B120.45 GiB