Quantization publisher
prism-ml
prism-ml publishes 6 quantizations across 3 models in our index, averaging 9.079 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
6
Models covered
3
Avg effective bpw
9.079
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | prism-ml | vs | Theirs | Difference |
|---|---|---|---|---|---|
| Ternary-Bonsai-4B-unpacked | F16 | 7.50 GiB | Rootkit7 | 7.50 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 |
|---|---|---|
| Ternary-Bonsai-8B-unpacked | 2 | 2.03 GiB |
| Ternary-Bonsai-4B-unpacked | 2 | 1.00 GiB |
| Ternary-Bonsai-1.7B-unpacked | 2 | 0.43 GiB |