DreamOmni2 · rafacost

DreamOmni2 Q6_K

This file is exactly 6,254,197,184 bytes — 5.82 GiB / 6.25 GB at an effective 6.570 bits per weight. The nominal rate for Q6_K is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

5.82 GiB · 1 file
llama.cpp
llama-cli -hf rafacost/DreamOmni2-7.6B-GGUF:Q6_K

Downloads and runs in one step, resolving the quantization by name.

Hugging Face CLI
hf download rafacost/DreamOmni2-7.6B-GGUF DreamOmni2-Vlm-Model-7.6B-Q6_K.gguf
Direct download

Straight from the Hugging Face CDN — we host nothing and earn nothing from this. Verify what you received against the exact byte count above; a size mismatch is the usual cause of a file that will not load.

Size
5.82 GiB
6.25 GB
Effective bpw
6.570
from real bytes ÷ params
Tensors
Header
GGUF metadata