WibbleWobble · mradermacher

WibbleWobble IQ4_XS

This file is exactly 4,484,363,232 bytes — 4.18 GiB / 4.48 GB at an effective 4.468 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

4.18 GiB · 1 file

llama.cpp

llama-cli -hf mradermacher/WibbleWobble-GGUF:IQ4_XS

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

Hugging Face CLI

hf download mradermacher/WibbleWobble-GGUF WibbleWobble.IQ4_XS.gguf

Direct download

WibbleWobble.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.

Repository →

Size

4.18 GiB

4.48 GB

Effective bpw

4.468

from real bytes ÷ params

Tensors

—

Header

—

GGUF metadata