L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit Q3_K_M
This file is exactly 10,266,271,328 bytes — 9.56 GiB / 10.27 GB at an effective 3.926 bits per weight. The nominal rate for Q3_K_M is lower; mixed-precision tensors make the real figure higher, always.
From the file· 1 file(s), summed
Get it
9.56 GiB · 1 file
llama.cpp
llama-cli -hf DavidAU/Llama-3.2-8X4B-MOE-V2-Dark-Champion-Instruct-uncensored-abliterated-21B-GGUF:Q3_K_M
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download DavidAU/Llama-3.2-8X4B-MOE-V2-Dark-Champion-Instruct-uncensored-abliterated-21B-GGUF L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit-D_AU-Q3_k_m.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
9.56 GiB
10.27 GB
Effective bpw
3.926
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata