Cosmos-Predict2-2B-Text2Image · calcuis

Cosmos-Predict2-2B-Text2Image Q4_K_M

This file is exactly 16,049,921,632 bytes — 14.95 GiB / 16.05 GB at an effective 9.001 bits per weight. The nominal rate for Q4_K_M is lower; mixed-precision tensors make the real figure higher, always.

From the file· 8 file(s), summed

Get it

14.95 GiB · 8 files

llama.cpp

llama-cli -hf calcuis/cosmos-predict2-gguf:Q4_K_M

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-q4_k_m.gguf"

This quantization is split across 8 files totalling 14.95 GiB. You need every part — the first is not a smaller version of the model.

Direct downloads — all 8 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

14.95 GiB

16.05 GB

Effective bpw

9.001

from real bytes ÷ params

Tensors

—

Header

—

GGUF metadata