Quantization publisher
Reza2kn
Reza2kn publishes 11 quantizations across 1 models in our index, averaging 5.749 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
11
Models covered
1
Avg effective bpw
5.749
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | Reza2kn | vs | Theirs | Difference |
|---|---|---|---|---|---|
| Qianfan-OCR | Q2_K | 1.68 GiB | DevQuasar | 1.68 GiB | -0.0% |
| Qianfan-OCR | Q3_K_M | 2.09 GiB | DevQuasar | 2.09 GiB | -0.0% |
| Qianfan-OCR | Q4_K_M | 2.54 GiB | DevQuasar | 2.54 GiB | -0.0% |
| Qianfan-OCR | Q5_K_M | 2.95 GiB | DevQuasar | 2.95 GiB | -0.0% |
| Qianfan-OCR | Q6_K | 3.38 GiB | DevQuasar | 3.38 GiB | -0.0% |
| Qianfan-OCR | Q8_0 | 4.38 GiB | DevQuasar | 4.38 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 |
|---|---|---|
| Qianfan-OCR | 11 | 1.68 GiB |