Quantization publisher
yaruti
yaruti publishes 4 quantizations across 1 models in our index, averaging 8.193 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 4 of the pairs we can compare — the same label does not mean the same file.
From the file· summed file bytes
Repositories
1
Quantizations
4
Models covered
1
Avg effective bpw
8.193
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | yaruti | vs | Theirs | Difference |
|---|---|---|---|---|---|
| Qwen3.5-9B-Base | Q5_K_M | 6.02 GiB | titan0115 | 6.07 GiB | -0.8% |
| Qwen3.5-9B-Base | Q4_K_M | 5.24 GiB | titan0115 | 5.24 GiB | 0.0% |
| Qwen3.5-9B-Base | Q8_0 | 8.87 GiB | titan0115 | 8.87 GiB | 0.0% |
| Qwen3.5-9B-Base | F16 | 16.69 GiB | titan0115 | 16.69 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 |
|---|---|---|
| Qwen3.5-9B-Base | 4 | 5.24 GiB |