Quantization publisher
anthracite-org
anthracite-org publishes 11 quantizations across 2 models in our index, averaging 5.478 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
11
Models covered
2
Avg effective bpw
5.478
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | anthracite-org | vs | Theirs | Difference |
|---|---|---|---|---|---|
| magnum-v2-12b | IQ3_M | 5.33 GiB | bartowski | 5.33 GiB | -0.0% |
| magnum-v2-12b | Q6_K | 9.37 GiB | bartowski | 9.37 GiB | -0.0% |
| magnum-v2-12b | Q8_0 | 12.13 GiB | bartowski | 12.13 GiB | -0.0% |
| magnum-v2.5-12b-kto | Q5_K_M | 8.13 GiB | bartowski | 8.13 GiB | -0.0% |
| magnum-v2.5-12b-kto | IQ3_M | 5.33 GiB | bartowski | 5.33 GiB | -0.0% |
| magnum-v2.5-12b-kto | Q8_0 | 12.13 GiB | bartowski | 12.13 GiB | -0.0% |
| magnum-v2.5-12b-kto | IQ4_XS | 6.28 GiB | bartowski | 6.28 GiB | -0.0% |
| magnum-v2.5-12b-kto | Q4_K_M | 6.96 GiB | bartowski | 6.96 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 |
|---|---|---|
| magnum-v2.5-12b-kto | 6 | 5.18 GiB |
| magnum-v2-12b | 5 | 5.33 GiB |