Quantization publisher
catlilface
catlilface publishes 2 quantizations across 2 models in our index, averaging 9.424 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
2
Quantizations
2
Models covered
2
Avg effective bpw
9.424
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | catlilface | vs | Theirs | Difference |
|---|---|---|---|---|---|
| Qwen3.6-35B-A3B-NVFP4-Fast | NVFP4 | 22.89 GiB | FreedomAISVR | 18.81 GiB | +21.7% |
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 |
|---|---|---|
| Qwen3.6-35B-A3B-NVFP4-Fast | 1 | 22.89 GiB |
| Gemma-4-26B-A4B-NVFP4 | 1 | 16.46 GiB |