Quantization publisher
anthonym21
anthonym21 publishes 2 quantizations across 1 models in our index, averaging 7.180 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 2 of the pairs we can compare — the same label does not mean the same file.
From the file· summed file bytes
Repositories
1
Quantizations
2
Models covered
1
Avg effective bpw
7.180
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | anthonym21 | vs | Theirs | Difference |
|---|---|---|---|---|---|
| dots.ocr | F16 | 3.32 GiB | ggml-org | 3.32 GiB | 0.0% |
| dots.ocr | Q8_0 | 1.76 GiB | ggml-org | 1.76 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 |
|---|---|---|
| dots.ocr | 2 | 1.76 GiB |