Quantization publisher
Jiunsong
Jiunsong publishes 3 quantizations across 3 models in our index, averaging 4.858 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 1 of the pairs we can compare — the same label does not mean the same file.
From the file· summed file bytes
Repositories
3
Quantizations
3
Models covered
3
Avg effective bpw
4.858
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | Jiunsong | vs | Theirs | Difference |
|---|---|---|---|---|---|
| SuperGemma-4-12b-abliterated | Q4_K_M | 6.87 GiB | mradermacher | 6.87 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 |
|---|---|---|
| SuperGemma-4-12b-abliterated | 1 | 6.87 GiB |
| SuperHY3-abliterated-NVFP4 | 1 | 95.10 GiB |
| SuperQwen-AgentWorld-35B-A3B-abliterated | 1 | 19.71 GiB |