Quantization publisher
8sp4rk
8sp4rk publishes 5 quantizations across 1 models in our index, averaging 5.745 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
5
Models covered
1
Avg effective bpw
5.745
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | 8sp4rk | vs | Theirs | Difference |
|---|---|---|---|---|---|
| Qwopus3.6-27B-Coder | Q8_0 | 26.63 GiB | Jackrong | 27.05 GiB | -1.6% |
| Qwopus3.6-27B-Coder | Q6_K | 20.57 GiB | Jackrong | 20.89 GiB | -1.6% |
| Qwopus3.6-27B-Coder | Q5_K_M | 17.91 GiB | Jackrong | 18.19 GiB | -1.6% |
| Qwopus3.6-27B-Coder | Q4_K_M | 15.41 GiB | Jackrong | 15.66 GiB | -1.6% |
| Qwopus3.6-27B-Coder | Q3_K_M | 12.39 GiB | Jackrong | 12.57 GiB | -1.5% |
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 |
|---|---|---|
| Qwopus3.6-27B-Coder | 5 | 12.39 GiB |