Quantization publisher
Melikshah
Melikshah publishes 4 quantizations across 1 models in our index, averaging 9.259 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 3 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
9.259
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | Melikshah | vs | Theirs | Difference |
|---|---|---|---|---|---|
| gpt-oss-20b-BF16 | F16 | 38.99 GiB | huihui-ai | 38.99 GiB | -0.0% |
| gpt-oss-20b-BF16 | Q4_K_M | 14.72 GiB | huihui-ai | 14.72 GiB | -0.0% |
| gpt-oss-20b-BF16 | Q8_0 | 20.73 GiB | huihui-ai | 20.73 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 |
|---|---|---|
| gpt-oss-20b-BF16 | 4 | 14.72 GiB |