Quantization publisher
Sci-fi-vy
Sci-fi-vy publishes 19 quantizations across 1 models in our index, averaging 3.499 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 2 of the pairs we can compare — the same label does not mean the same file.
From the file· summed file bytes
Repositories
1
Quantizations
19
Models covered
1
Avg effective bpw
3.499
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | Sci-fi-vy | vs | Theirs | Difference |
|---|---|---|---|---|---|
| Qwen2.5-Omni-7B | Q8_0 | 7.54 GiB | ggml-org | 7.54 GiB | 0.0% |
| Qwen2.5-Omni-7B | Q4_K_M | 4.36 GiB | ggml-org | 4.36 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 |
|---|---|---|
| Qwen2.5-Omni-7B | 19 | 1.93 GiB |