Quantization publisher
ash2813
ash2813 publishes 2 quantizations across 1 models in our index, averaging 10.682 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 2 of the pairs we can compare — the same label does not mean the same file.
From the file· summed file bytes
Repositories
1
Quantizations
2
Models covered
1
Avg effective bpw
10.682
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | ash2813 | vs | Theirs | Difference |
|---|---|---|---|---|---|
| llm-jp-4-32b-a3b-thinking | Q4_K_M | 20.04 GiB | mmnga-o | 19.93 GiB | +0.6% |
| llm-jp-4-32b-a3b-thinking | Q4_K_M | 20.04 GiB | hiratagoh | 19.93 GiB | +0.6% |
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 |
|---|---|---|
| llm-jp-4-32b-a3b-thinking | 2 | 20.04 GiB |