FireRedPunc · cstr
FireRedPunc IQ4_XS
This file is exactly 54,707,712 bytes — 0.05 GiB / 0.05 GB at an effective 4.304 bits per weight. The nominal rate for IQ4_XS is lower; mixed-precision tensors make the real figure higher, always.
From the file· 1 file(s), summed
Get it
0.05 GiB · 1 file
llama.cpp
llama-cli -hf cstr/fireredpunc-GGUF:IQ4_XS
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download cstr/fireredpunc-GGUF fireredpunc-iq4_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
0.05 GiB
0.05 GB
Effective bpw
4.304
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata