SeedVR2_comfyUI · cmeka
SeedVR2_comfyUI Q3_K_M
This file is exactly 8,903,786,400 bytes — 8.29 GiB / 8.90 GB at an effective 21.003 bits per weight. The nominal rate for Q3_K_M is lower; mixed-precision tensors make the real figure higher, always.
From the file· 3 file(s), summed
Get it
8.29 GiB · 3 files
llama.cpp
llama-cli -hf cmeka/SeedVR2-GGUF:Q3_K_M
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download cmeka/SeedVR2-GGUF --include "seedvr2_ema_3b-Q3_K_M.gguf"
This quantization is split across 3 files totalling 8.29 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
8.29 GiB
8.90 GB
Effective bpw
21.003
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata