Quantization publisher
SAPSAN-SKLEP
SAPSAN-SKLEP publishes 4 quantizations across 1 models in our index, averaging 5.730 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 4 of the pairs we can compare — the same label does not mean the same file.
From the file· summed file bytes
Repositories
1
Quantizations
4
Models covered
1
Avg effective bpw
5.730
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | SAPSAN-SKLEP | vs | Theirs | Difference |
|---|---|---|---|---|---|
| Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated | Q3_K_M | 13.70 GiB | mradermacher | 13.70 GiB | -0.0% |
| Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated | Q4_K_M | 17.28 GiB | mradermacher | 17.28 GiB | -0.0% |
| Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated | Q5_K_M | 20.23 GiB | mradermacher | 20.23 GiB | -0.0% |
| Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated | Q8_0 | 30.25 GiB | mradermacher | 30.25 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 |
|---|---|---|
| Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated | 4 | 13.70 GiB |