Quantization publisher
dahara1
dahara1 publishes 28 quantizations across 2 models in our index, averaging 4.933 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 8 of the pairs we can compare — the same label does not mean the same file.
From the file· summed file bytes
Repositories
2
Quantizations
28
Models covered
2
Avg effective bpw
4.933
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | dahara1 | vs | Theirs | Difference |
|---|---|---|---|---|---|
| gemma-4-E4B-it | Q4_K_M | 4.64 GiB | trjxter | 4.97 GiB | -6.7% |
| gemma-4-E4B-it | Q4_K_M | 4.64 GiB | pankajpandey-dev | 4.97 GiB | -6.7% |
| gemma-4-E4B-it | Q5_K_M | 5.11 GiB | trjxter | 5.37 GiB | -4.9% |
| gemma-4-E4B-it | Q5_K_M | 5.11 GiB | pankajpandey-dev | 5.37 GiB | -4.9% |
| gemma-4-E4B-it | Q6_K | 5.95 GiB | trjxter | 5.79 GiB | +2.8% |
| gemma-4-E4B-it | Q8_0 | 7.63 GiB | pankajpandey-dev | 7.48 GiB | +2.0% |
| gemma-4-E4B-it | Q8_0 | 7.63 GiB | trjxter | 7.48 GiB | +2.0% |
| gemma-4-E2B-it | Q8_0 | 4.70 GiB | Alienstro | 4.63 GiB | +1.6% |
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 | 14 | 3.29 GiB |
| gemma-4-E2B-it | 14 | 2.13 GiB |