Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B IQ4_XS
This file is exactly 20,823,411,328 bytes — 19.39 GiB / 20.82 GB at an effective 9.051 bits per weight. The nominal rate for IQ4_XS is lower; mixed-precision tensors make the real figure higher, always.
From the file· 2 file(s), summed
Get it
19.39 GiB · 2 files
llama.cpp
llama-cli -hf DavidAU/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B-GGUF:IQ4_XS
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 --include "L3.2-8X3B-GATED-MOE-RSN-Dark-Champion-Inst-18.4B-uncen-ablit_D_AU-IQ4_XS.gguf"
This quantization is split across 2 files totalling 19.39 GiB. You need every part — the first is not a smaller version of the model.
Direct downloads — all 2 required
- L3.2-8X3B-GATED-MOE-RSN-Dark-Champion-Inst-18.4B-uncen-ablit_D_AU-IQ4_XS.gguf
- L3.2-8X3B-GATED-MOE-RSN-Dark-Champion-Inst-18.4B-uncen-ablit_PLUS_D_AU-IQ4_XS.gguf
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
19.39 GiB
20.82 GB
Effective bpw
9.051
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata