LTX-Video · calcuis

LTX-Video Q8_0

This file is exactly 4,347,782,144 bytes — 4.05 GiB / 4.35 GB at an effective 18.084 bits per weight. The nominal rate for Q8_0 is lower; mixed-precision tensors make the real figure higher, always.

From the file· 2 file(s), summed

Get it

4.05 GiB · 2 files
llama.cpp
llama-cli -hf calcuis/ltxv0.9.6-gguf:Q8_0

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

Hugging Face CLI
hf download calcuis/ltxv0.9.6-gguf --include "ltxv-2b-0.9.6-dev-q8_0.gguf"

This quantization is split across 2 files totalling 4.05 GiB. You need every part — the first is not a smaller version of the model.

Direct downloads — all 2 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
4.05 GiB
4.35 GB
Effective bpw
18.084
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata