HunyuanVideo · calcuis

HunyuanVideo Q4_0

This file is exactly 20,160,501,760 bytes — 18.78 GiB / 20.16 GB at an effective 12.580 bits per weight. The nominal rate for Q4_0 is lower; mixed-precision tensors make the real figure higher, always.

From the file· 3 file(s), summed

Get it

18.78 GiB · 3 files
llama.cpp
llama-cli -hf calcuis/hyvid:Q4_0

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

Hugging Face CLI
hf download calcuis/hyvid --include "fast-hunyuan-video-t2v-720p-q4_0.gguf"

This quantization is split across 3 files totalling 18.78 GiB. You need every part — the first is not a smaller version of the model.

Direct downloads — all 3 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.

Size
18.78 GiB
20.16 GB
Effective bpw
12.580
from real bytes ÷ params
Tensors
Header
GGUF metadata