LTX-Video · calcuis
LTX-Video Q3_K_M
This file is exactly 2,158,879,744 bytes — 2.01 GiB / 2.16 GB at an effective 8.979 bits per weight. The nominal rate for Q3_K_M is lower; mixed-precision tensors make the real figure higher, always.
From the file· 2 file(s), summed
Get it
2.01 GiB · 2 files
llama.cpp
llama-cli -hf calcuis/ltxv0.9.6-gguf:Q3_K_M
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-q3_k_m.gguf"
This quantization is split across 2 files totalling 2.01 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.
Size
2.01 GiB
2.16 GB
Effective bpw
8.979
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata