Quantization publisher
keyserkazi
keyserkazi publishes 5 quantizations across 1 models in our index, averaging 5.149 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
5
Models covered
1
Avg effective bpw
5.149
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | keyserkazi | vs | Theirs | Difference |
|---|---|---|---|---|---|
| gemma-4-E4B-it | Q3_K_M | 4.52 GiB | unsloth | 3.78 GiB | +19.5% |
| gemma-4-E4B-it | Q4_K_M | 4.97 GiB | unsloth | 4.64 GiB | +7.2% |
| gemma-4-E4B-it | IQ4_XS | 4.72 GiB | unsloth | 4.39 GiB | +7.5% |
| gemma-4-E4B-it | Q5_K_M | 5.37 GiB | unsloth | 5.11 GiB | +5.1% |
| gemma-4-E4B-it | Q4_K_M | 4.97 GiB | lmstudio-community | 4.97 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 | 5 | 4.39 GiB |