Quantization publisher
csoares31
csoares31 publishes 3 quantizations across 1 models in our index, averaging 9.796 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 4 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
9.796
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | csoares31 | vs | Theirs | Difference |
|---|---|---|---|---|---|
| AMALIA-9B-0626-DPO | Q4_K_M | 5.20 GiB | duarteocarmo | 5.20 GiB | 0.0% |
| AMALIA-9B-0626-DPO | Q8_0 | 9.06 GiB | duarteocarmo | 9.06 GiB | 0.0% |
| AMALIA-9B-0626-DPO | Q4_K_M | 5.20 GiB | layerx-labs | 5.20 GiB | -0.0% |
| AMALIA-9B-0626-DPO | Q8_0 | 9.06 GiB | layerx-labs | 9.06 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 |
|---|---|---|
| AMALIA-9B-0626-DPO | 3 | 5.20 GiB |