Quantization publisher
DollasAndSpence
DollasAndSpence publishes 6 quantizations across 1 models in our index, averaging 7.685 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 5 of the pairs we can compare — the same label does not mean the same file.
From the file· summed file bytes
Repositories
1
Quantizations
6
Models covered
1
Avg effective bpw
7.685
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | DollasAndSpence | vs | Theirs | Difference |
|---|---|---|---|---|---|
| gemma-4-E4B-it-ultra-uncensored-heretic | Q6_K | 5.79 GiB | mradermacher | 5.79 GiB | 0.0% |
| gemma-4-E4B-it-ultra-uncensored-heretic | Q8_0 | 7.48 GiB | mradermacher | 7.48 GiB | 0.0% |
| gemma-4-E4B-it-ultra-uncensored-heretic | Q4_K_M | 4.97 GiB | mradermacher | 4.97 GiB | 0.0% |
| gemma-4-E4B-it-ultra-uncensored-heretic | Q5_K_M | 5.37 GiB | mradermacher | 5.37 GiB | 0.0% |
| gemma-4-E4B-it-ultra-uncensored-heretic | Q5_K_S | 5.30 GiB | mradermacher | 5.30 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-E4B-it-ultra-uncensored-heretic | 6 | 4.97 GiB |