Quantization publisher
morikomorizz
morikomorizz publishes 15 quantizations across 2 models in our index, averaging 5.704 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 9 of the pairs we can compare — the same label does not mean the same file.
From the file· summed file bytes
Repositories
2
Quantizations
15
Models covered
2
Avg effective bpw
5.704
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | morikomorizz | vs | Theirs | Difference |
|---|---|---|---|---|---|
| GRM-2.6-Plus-0628 | Q3_K_M | 15.81 GiB | bartowski | 13.60 GiB | +16.2% |
| GRM-2.6-Plus-0628 | Q8_0 | 28.87 GiB | bartowski | 27.12 GiB | +6.5% |
| GRM-2.6-Plus-0628 | Q5_K_M | 20.03 GiB | bartowski | 19.33 GiB | +3.6% |
| GRM-2.6-Plus-0628 | IQ2_M | 10.72 GiB | bartowski | 10.13 GiB | +5.9% |
| GRM-2.6-Plus-0628 | Q4_K_M | 17.12 GiB | bartowski | 16.55 GiB | +3.4% |
| GRM-2.6-Plus-0628 | IQ4_NL | 15.73 GiB | bartowski | 15.20 GiB | +3.5% |
| GRM-2.6-Plus-0628 | IQ4_XS | 14.85 GiB | bartowski | 14.50 GiB | +2.4% |
| GRM-2.6-Plus-0628 | IQ3_M | 12.78 GiB | bartowski | 12.95 GiB | -1.3% |
| GRM-2.6-Plus-0628 | BF16 | 50.90 GiB | bartowski | 50.90 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 |
|---|---|---|
| Qwopus3.5-122B-A10B-Kimi-K2.6-destill-healed-abliterated | 3 | 55.04 GiB |
| GRM-2.6-Plus-0628 | 12 | 8.62 GiB |