Quantization publisher
Paulescu
Paulescu publishes 3 quantizations across 1 models in our index, averaging 9.535 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
3
Models covered
1
Avg effective bpw
9.535
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | Paulescu | vs | Theirs | Difference |
|---|---|---|---|---|---|
| LFM2.5-Audio-1.5B | F16 | 2.68 GiB | LiquidAI | 2.68 GiB | -0.0% |
| LFM2.5-Audio-1.5B | Q4_0 | 0.80 GiB | LiquidAI | 0.80 GiB | -0.0% |
| LFM2.5-Audio-1.5B | Q8_0 | 1.42 GiB | LiquidAI | 1.42 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 |
|---|---|---|
| LFM2.5-Audio-1.5B | 3 | 0.80 GiB |