Quantization publisher
sahilchachra
sahilchachra publishes 13 quantizations across 1 models in our index, averaging 5.276 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
1
Quantizations
13
Models covered
1
Avg effective bpw
5.276
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | sahilchachra | vs | Theirs | Difference |
|---|---|---|---|---|---|
| Unlimited-OCR | Q6_K | 2.43 GiB | DevQuasar | 2.43 GiB | 0.0% |
| Unlimited-OCR | Q8_0 | 2.91 GiB | DevQuasar | 2.91 GiB | 0.0% |
| Unlimited-OCR | Q4_K_M | 1.82 GiB | DevQuasar | 1.82 GiB | 0.0% |
| Unlimited-OCR | Q3_K_M | 1.45 GiB | DevQuasar | 1.45 GiB | 0.0% |
| Unlimited-OCR | Q5_K_M | 2.07 GiB | DevQuasar | 2.07 GiB | 0.0% |
| Unlimited-OCR | Q8_0 | 2.91 GiB | sabafallah | 2.91 GiB | 0.0% |
| Unlimited-OCR | Q4_K_M | 1.82 GiB | sabafallah | 1.82 GiB | 0.0% |
| Unlimited-OCR | BF16 | 5.47 GiB | sabafallah | 5.47 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 |
|---|---|---|
| Unlimited-OCR | 13 | 1.15 GiB |