Quantization publisher
DevQuasar-11
DevQuasar-11 publishes 7 quantizations across 1 models in our index, averaging 4.224 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 5 of the pairs we can compare — the same label does not mean the same file.
From the file· summed file bytes
Repositories
1
Quantizations
7
Models covered
1
Avg effective bpw
4.224
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | DevQuasar-11 | vs | Theirs | Difference |
|---|---|---|---|---|---|
| cogito-671b-v2.1 | Q2_K | 227.38 GiB | unsloth | 228.82 GiB | -0.6% |
| cogito-671b-v2.1 | Q3_K_M | 297.34 GiB | unsloth | 298.44 GiB | -0.4% |
| cogito-671b-v2.1 | Q4_K_M | 376.71 GiB | unsloth | 377.55 GiB | -0.2% |
| cogito-671b-v2.1 | Q5_K_M | 442.77 GiB | unsloth | 443.46 GiB | -0.2% |
| cogito-671b-v2.1 | Q8_0 | 664.29 GiB | unsloth | 664.29 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 |
|---|---|---|
| cogito-671b-v2.1 | 7 | 138.82 GiB |