Quantization publisher
GrahLnn
GrahLnn publishes 3 quantizations across 1 models in our index, averaging 3.880 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 6 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
3.880
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | GrahLnn | vs | Theirs | Difference |
|---|---|---|---|---|---|
| Hy-MT2-30B-A3B | Q2_K | 10.30 GiB | mradermacher | 10.30 GiB | -0.0% |
| Hy-MT2-30B-A3B | Q3_K_M | 13.45 GiB | mradermacher | 13.45 GiB | -0.0% |
| Hy-MT2-30B-A3B | Q4_K_M | 16.98 GiB | mradermacher | 16.98 GiB | -0.0% |
| Hy-MT2-30B-A3B | Q2_K | 10.30 GiB | litigerking | 10.30 GiB | -0.0% |
| Hy-MT2-30B-A3B | Q3_K_M | 13.45 GiB | litigerking | 13.45 GiB | -0.0% |
| Hy-MT2-30B-A3B | Q4_K_M | 16.98 GiB | litigerking | 16.98 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 |
|---|---|---|
| Hy-MT2-30B-A3B | 3 | 10.30 GiB |