aya-23-8B · bartowski

aya-23-8B IQ2_XS

This file is exactly 2,795,662,464 bytes — 2.60 GiB / 2.80 GB at an effective 2.786 bits per weight. The nominal rate for IQ2_XS is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

2.60 GiB · 1 file

llama.cpp

llama-cli -hf bartowski/aya-23-8B-GGUF:IQ2_XS

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

Hugging Face CLI

hf download bartowski/aya-23-8B-GGUF aya-23-8B-IQ2_XS.gguf

Direct download

aya-23-8B-IQ2_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

2.60 GiB

2.80 GB

Effective bpw

2.786

from real bytes ÷ params

Tensors

—

Header

—

GGUF metadata