SeedVR2-3B · AInVFX
SeedVR2-3B Q8_0
This file is exactly 3,660,613,984 bytes — 3.41 GiB / 3.66 GB at an effective 8.635 bits per weight. The nominal rate for Q8_0 is lower; mixed-precision tensors make the real figure higher, always.
From the file· 1 file(s), summedFrom the file· 635 tensors parsed
Get it
3.41 GiB · 1 file
llama.cpp
llama-cli -hf AInVFX/SeedVR2_comfyUI:Q8_0
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download AInVFX/SeedVR2_comfyUI seedvr2_ema_3b-Q8_0.gguf
Direct download
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
3.41 GiB
3.66 GB
Effective bpw
8.635
from real bytes ÷ params
Tensors
635
Header
0.04 MB
GGUF metadata
What this quantization actually contains
per-tensor types, parsed from the GGUF header
F16
425
Q8_0
210
A quantization label names a mixture, not a uniform precision. Attention and output tensors are routinely kept at higher precision than the label implies, which is exactly why the effective bits-per-weight above exceeds the nominal rate.