Cosmos-Predict2-2B-Text2Image · calcuis
Cosmos-Predict2-2B-Text2Image Q6_K
This file is exactly 70,505,718,624 bytes — 65.66 GiB / 70.51 GB.
From the file· 12 file(s), summed
Get it
65.66 GiB · 12 files
llama.cpp
llama-cli -hf calcuis/cosmos-predict2-gguf:Q6_K
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-q6_k.gguf"
This quantization is split across 12 files totalling 65.66 GiB. You need every part — the first is not a smaller version of the model.
Direct downloads — all 12 required
- cosmos-predict2-14b-t2i-ex3-q6_k.gguf
- cosmos-predict2-14b-v2w-480p-10fps-ex3-q6_k.gguf
- cosmos-predict2-14b-v2w-480p-16fps-ex3-q6_k.gguf
- cosmos-predict2-14b-v2w-720p-10fps-ex3-q6_k.gguf
- cosmos-predict2-14b-v2w-720p-16fps-ex3-q6_k.gguf
- cosmos-predict2-2b-t2i-ex3-q6_k.gguf
- cosmos-predict2-2b-t2i-ex-q6_k.gguf
- cosmos-predict2-2b-v2w-480p-10fps-ex3-q6_k.gguf
- cosmos-predict2-2b-v2w-480p-16fps-ex3-q6_k.gguf
- cosmos-predict2-2b-v2w-720p-10fps-ex3-q6_k.gguf
- cosmos-predict2-2b-v2w-720p-16fps-ex3-q6_k.gguf
- cosmos-predict2-2b-v2w-720p-16fps-ex-q6_k.gguf
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
65.66 GiB
70.51 GB
Effective bpw
—
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata