Quantization publisher
kai-os
kai-os publishes 7 quantizations across 2 models in our index, averaging 6.508 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 7 of the pairs we can compare — the same label does not mean the same file.
From the file· summed file bytes
Repositories
2
Quantizations
7
Models covered
2
Avg effective bpw
6.508
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | kai-os | vs | Theirs | Difference |
|---|---|---|---|---|---|
| Carnice-V2-27b | Q5_K_M | 17.91 GiB | bartowski | 19.10 GiB | -6.3% |
| Carnice-V2-27b | Q4_K_M | 15.41 GiB | bartowski | 16.33 GiB | -5.6% |
| Carnice-V2-27b | Q2_K | 9.98 GiB | bartowski | 10.80 GiB | -7.7% |
| Carnice-V2-27b | IQ2_M | 9.32 GiB | bartowski | 9.90 GiB | -5.9% |
| Grug-12B | Q4_K_M | 6.87 GiB | bartowski | 7.14 GiB | -3.7% |
| Carnice-V2-27b | Q8_0 | 26.63 GiB | bartowski | 26.70 GiB | -0.2% |
| Carnice-V2-27b | BF16 | 50.11 GiB | bartowski | 50.11 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 |
|---|---|---|
| Grug-12B | 1 | 6.87 GiB |
| Carnice-V2-27b | 6 | 9.32 GiB |