Quantization format
Q2_K_M
Q2_K_M has a nominal rate of — bits per weight. We have no measured files carrying this label yet.
From the file· 8 files measured
Nominal bpw
—
from the block layout
Measured average
3.451
8 files
Range
2.895–4.210
varies by architecture
File sizes
1.70 GiB+
up to 12.61 GiB
Real files
one per model, most downloaded first
| Model | Size● | Effective bpw● | vs nominal● |
|---|---|---|---|
| GRM-2.6-Plus-0628 | 12.61 GiB | 3.898 | — |
| gemma-4-12B | 4.57 GiB | 3.280 | — |
| Ministral-3-8B-Instruct-2512-BF16 | 3.44 GiB | 3.313 | — |
| granite-3.1-8b-instruct | 2.85 GiB | 2.992 | — |
| Magistral-Small-2509-Vision | 8.09 GiB | 2.895 | — |
| orpheus-3b-0.1-pretrained | 1.70 GiB | 3.855 | — |
| Pixtral-12B-2409 | 6.00 GiB | 4.210 | — |
| MiniMax-H3 | 12.20 GiB | 3.164 | — |
●From the filewhat these mean