Quantization publisher
LocalAI-io
LocalAI-io publishes 3 quantizations across 3 models in our index, averaging 12.376 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
12.376
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | LocalAI-io | vs | Theirs | Difference |
|---|---|---|---|---|---|
| privacy-filter-multilingual | F16 | 2.62 GiB | sumeshi | 2.62 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 |
|---|---|---|
| LocalAI-functioncall-qwen2.5-7b-v0.5 | 1 | 4.36 GiB |
| privacy-filter-nemotron | 1 | 2.62 GiB |
| privacy-filter-multilingual | 1 | 2.62 GiB |