Quantization publisher
OrdenWills
OrdenWills publishes 3 quantizations across 1 models in our index, averaging 9.896 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 5 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
9.896
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | OrdenWills | vs | Theirs | Difference |
|---|---|---|---|---|---|
| LFM2.5-350M | F16 | 0.66 GiB | LiquidAI | 0.66 GiB | -0.3% |
| LFM2.5-350M | Q8_0 | 0.35 GiB | lazos | 0.35 GiB | -0.3% |
| LFM2.5-350M | Q8_0 | 0.35 GiB | LiquidAI | 0.35 GiB | -0.3% |
| LFM2.5-350M | Q4_K_M | 0.21 GiB | lazos | 0.21 GiB | -0.4% |
| LFM2.5-350M | Q4_K_M | 0.21 GiB | LiquidAI | 0.21 GiB | -0.4% |
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 |
|---|---|---|
| LFM2.5-350M | 3 | 0.21 GiB |