Quantization publisher

DavCd

DavCd publishes 4 quantizations across 1 models in our index, averaging 6.386 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 3 of the pairs we can compare — the same label does not mean the same file.

From the file· summed file bytes
Repositories
1
Quantizations
4
Models covered
1
Avg effective bpw
6.386
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuantDavCdvsTheirsDifference
gemma-4-26B-A4B-it-heretic-ara-v2Q4_K_M16.51 GiBmradermacher15.64 GiB+5.5%
gemma-4-26B-A4B-it-heretic-ara-v2Q5_K_M18.52 GiBmradermacher17.82 GiB+3.9%
gemma-4-26B-A4B-it-heretic-ara-v2Q6_K21.58 GiBmradermacher21.08 GiB+2.4%

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
gemma-4-26B-A4B-it-heretic-ara-v2416.51 GiB