Quantization publisher

Danny-Dasilva

Danny-Dasilva publishes 3 quantizations across 2 models in our index, averaging 8.764 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
3
Models covered
2
Avg effective bpw
8.764
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuantDanny-DasilvavsTheirsDifference
Ternary-Bonsai-27B-ggufQ2_07.68 GiBHikari07jp6.67 GiB+15.1%
Ternary-Bonsai-27B-ggufQ2_07.68 GiBdealignai7.68 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
Ternary-Bonsai-27B-gguf21.81 GiB
Bonsai-27B-gguf11.66 GiB