c4ai-command-r-v01 IQ3_XS

This file is exactly 30,182,832,000 bytes — 28.11 GiB / 30.18 GB at an effective 6.903 bits per weight. The nominal rate for IQ3_XS is lower; mixed-precision tensors make the real figure higher, always.

From the file· 2 file(s), summed

Get it

28.11 GiB · 2 files
llama.cpp
llama-cli -hf DavidAU/Command-R-01-Ultra-NEO-DARK-HORROR-V1-V2-35B-IMATRIX-GGUF:IQ3_XS

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

Hugging Face CLI
hf download DavidAU/Command-R-01-Ultra-NEO-DARK-HORROR-V1-V2-35B-IMATRIX-GGUF --include "Command-R-35B-Dark-Horror-V1-IQ3_XS.gguf"

This quantization is split across 2 files totalling 28.11 GiB. You need every part — the first is not a smaller version of the model.

Direct downloads — all 2 required

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
28.11 GiB
30.18 GB
Effective bpw
6.903
from real bytes ÷ params
Tensors
Header
GGUF metadata
c4ai-command-r-v01 IQ3_XS — exact size and VRAM — ossmodeldb