Cosmos-Predict2-2B-Text2Image · calcuis

Cosmos-Predict2-2B-Text2Image Q5_0

This file is exactly 81,925,395,520 bytes — 76.30 GiB / 81.93 GB.

From the file· 16 file(s), summed

Get it

76.30 GiB · 16 files
llama.cpp
llama-cli -hf calcuis/cosmos-predict2-gguf:Q5_0

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

Hugging Face CLI
hf download calcuis/cosmos-predict2-gguf --include "cosmos-predict2-14b-t2i-ex3-q5_0.gguf"

This quantization is split across 16 files totalling 76.30 GiB. You need every part — the first is not a smaller version of the model.

Direct downloads — all 16 required

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.

Repository →
Size
76.30 GiB
81.93 GB
Effective bpw
—
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata