Quantization publisher
AngelSlim
AngelSlim publishes 3 quantizations across 1 models in our index, averaging 3.627 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
3.627
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | AngelSlim | vs | Theirs | Difference |
|---|---|---|---|---|---|
| Hy3 | IQ1_M | 83.30 GiB | bartowski | 66.22 GiB | +25.8% |
| Hy3 | Q3_K_M | 125.35 GiB | vcruz305 | 132.94 GiB | -5.7% |
| Hy3 | Q3_K_M | 125.35 GiB | bartowski | 128.10 GiB | -2.1% |
| Hy3 | IQ1_M | 83.30 GiB | vcruz305 | 85.45 GiB | -2.5% |
| Hy3 | Q4_K_M | 169.81 GiB | vcruz305 | 168.57 GiB | +0.7% |
| Hy3 | Q4_K_M | 169.81 GiB | bartowski | 169.65 GiB | +0.1% |
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 |
|---|---|---|
| Hy3 | 3 | 83.30 GiB |