Quantization publisher
pankajpandey-dev
pankajpandey-dev publishes 3 quantizations across 1 models in our index, averaging 6.380 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 6 of the pairs we can compare — the same label does not mean the same file.
From the file· summed file bytes
Repositories
1
Quantizations
3
Models covered
1
Avg effective bpw
6.380
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | pankajpandey-dev | vs | Theirs | Difference |
|---|---|---|---|---|---|
| gemma-4-E4B-it | Q4_K_M | 4.97 GiB | dahara1 | 4.64 GiB | +7.2% |
| gemma-4-E4B-it | Q5_K_M | 5.37 GiB | dahara1 | 5.11 GiB | +5.1% |
| gemma-4-E4B-it | Q8_0 | 7.48 GiB | dahara1 | 7.63 GiB | -2.0% |
| gemma-4-E4B-it | Q4_K_M | 4.97 GiB | trjxter | 4.97 GiB | -0.0% |
| gemma-4-E4B-it | Q5_K_M | 5.37 GiB | trjxter | 5.37 GiB | -0.0% |
| gemma-4-E4B-it | Q8_0 | 7.48 GiB | trjxter | 7.48 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 | 3 | 4.97 GiB |