Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B Q6_K

This file is exactly 15,615,851,840 bytes — 14.54 GiB / 15.62 GB at an effective 6.788 bits per weight. The nominal rate for Q6_K is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

14.54 GiB · 1 file
llama.cpp
llama-cli -hf DavidAU/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B-GGUF:Q6_K

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

Hugging Face CLI
hf download DavidAU/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B-GGUF L3.2-8X3B-GATED-MOE-RSN-Dark-Champion-Inst-18.4B-uncen-ablit_D_AU-Q6_k.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
14.54 GiB
15.62 GB
Effective bpw
6.788
from real bytes ÷ params
Tensors
Header
GGUF metadata
Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B Q6_K — exact size and VRAM — ossmodeldb