Quantization publisher
PeterAM4
PeterAM4 publishes 7 quantizations across 1 models in our index, averaging 7.889 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 5 of the pairs we can compare — the same label does not mean the same file.
From the file· summed file bytes
Repositories
1
Quantizations
7
Models covered
1
Avg effective bpw
7.889
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | PeterAM4 | vs | Theirs | Difference |
|---|---|---|---|---|---|
| Qwen3-Embedding-0.6B | Q5_K_M | 0.41 GiB | mradermacher | 0.41 GiB | -0.0% |
| Qwen3-Embedding-0.6B | Q5_K_S | 0.41 GiB | mradermacher | 0.41 GiB | -0.0% |
| Qwen3-Embedding-0.6B | Q6_K | 0.46 GiB | mradermacher | 0.46 GiB | -0.0% |
| Qwen3-Embedding-0.6B | Q8_0 | 0.60 GiB | mradermacher | 0.60 GiB | -0.0% |
| Qwen3-Embedding-0.6B | Q8_0 | 0.60 GiB | xthor | 0.60 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 |
|---|---|---|
| Qwen3-Embedding-0.6B | 7 | 0.41 GiB |