Quantization publisher
poolside
poolside publishes 5 quantizations across 2 models in our index, averaging 10.432 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 8 of the pairs we can compare — the same label does not mean the same file.
From the file· summed file bytes
Repositories
2
Quantizations
5
Models covered
2
Avg effective bpw
10.432
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | poolside | vs | Theirs | Difference |
|---|---|---|---|---|---|
| Laguna-S-2.1 | Q4_K_M | 89.44 GiB | lmstudio-community | 66.28 GiB | +34.9% |
| Laguna-S-2.1 | Q4_K_M | 89.44 GiB | bartowski | 66.83 GiB | +33.8% |
| Laguna-S-2.1 | Q8_0 | 119.91 GiB | lmstudio-community | 116.44 GiB | +3.0% |
| Laguna-S-2.1 | Q8_0 | 119.91 GiB | bartowski | 116.44 GiB | +3.0% |
| Laguna-S-2.1 | Q8_0 | 119.91 GiB | unsloth | 116.44 GiB | +3.0% |
| Laguna-XS-2.1 | Q4_K_M | 18.88 GiB | bartowski | 19.14 GiB | -1.3% |
| Laguna-XS-2.1 | BF16 | 62.33 GiB | bartowski | 62.33 GiB | -0.0% |
| Laguna-XS-2.1 | Q4_K_M | 18.88 GiB | lmstudio-community | 18.88 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 |
|---|---|---|
| Laguna-XS-2.1 | 2 | 18.88 GiB |
| Laguna-S-2.1 | 3 | 89.44 GiB |