Quantization publisher
jfiekdjdk
jfiekdjdk publishes 5 quantizations across 2 models in our index, averaging 6.225 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
2
Quantizations
5
Models covered
2
Avg effective bpw
6.225
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | jfiekdjdk | vs | Theirs | Difference |
|---|---|---|---|---|---|
| gemma-4-31b-it-heretic-ara | Q4_K_M | 17.40 GiB | mradermacher | 17.40 GiB | -0.0% |
| gemma-4-31b-it-heretic-ara | Q6_K | 23.47 GiB | mradermacher | 23.47 GiB | -0.0% |
| gemma-4-31b-it-heretic-ara | Q8_0 | 30.39 GiB | mradermacher | 30.39 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-heretic-ara | 4 | 16.44 GiB |
| GLM-4-9B-0414-abliterated | 1 | 7.70 GiB |