DreamOmni2 · rafacost

DreamOmni2 F16

This file is exactly 15,237,851,584 bytes — 14.19 GiB / 15.24 GB at an effective 16.007 bits per weight. The nominal rate for F16 is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

14.19 GiB · 1 file
llama.cpp
llama-cli -hf rafacost/DreamOmni2-7.6B-GGUF:F16

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-F16.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
14.19 GiB
15.24 GB
Effective bpw
16.007
from real bytes ÷ params
Tensors
Header
GGUF metadata
DreamOmni2 F16 — exact size and VRAM — ossmodeldb