Quantization format

Q6_K_M

Q6_K_M has a nominal rate of bits per weight. We have no measured files carrying this label yet.

From the file· 10 files measured
Nominal bpw
from the block layout
Measured average
6.415
10 files
Range
3.644–7.657
varies by architecture
File sizes
0.41 GiB+
up to 24.76 GiB

Real files

one per model, most downloaded first
ModelSizeEffective bpwvs nominal
GRM-2.6-Plus-062824.76 GiB7.657
LFM2-1.2B0.90 GiB6.582
gemma-4-12B9.34 GiB6.709
LFM2-2.6B1.97 GiB6.572
Ministral-3-8B-Instruct-2512-BF166.98 GiB6.720
granite-3.1-8b-instruct6.24 GiB6.565
PaddleOCR-VL-1.50.41 GiB3.644
Magistral-Small-2509-Vision18.32 GiB6.554
orpheus-3b-0.1-pretrained2.90 GiB6.582
granite-3.1-2b-instruct1.94 GiB6.570
From the filewhat these mean

Other quantizations