L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit · mradermacher
L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit I1-IQ2_XS
This file is exactly 6,438,375,936 bytes — 6.00 GiB / 6.44 GB at an effective 2.462 bits per weight. The nominal rate for I1-IQ2_XS is lower; mixed-precision tensors make the real figure higher, always.
From the file· 1 file(s), summed
Get it
6.00 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit-i1-GGUF:I1-IQ2_XS
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download mradermacher/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit-i1-GGUF L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit.i1-IQ2_XS.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
6.00 GiB
6.44 GB
Effective bpw
2.462
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata