Quantization publisher
CountCandy
CountCandy publishes 2 quantizations across 1 models in our index, averaging 5.614 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 1 of the pairs we can compare — the same label does not mean the same file.
From the file· summed file bytes
Repositories
1
Quantizations
2
Models covered
1
Avg effective bpw
5.614
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | CountCandy | vs | Theirs | Difference |
|---|---|---|---|---|---|
| gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking | Q6_K | 23.47 GiB | mradermacher | 23.47 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
| Model | Quantizations | Smallest |
|---|---|---|
| gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking | 2 | 17.40 GiB |