aya-23-8B · legraphista

aya-23-8B Q5_K

This file is exactly 5,803,568,000 bytes — 5.40 GiB / 5.80 GB at an effective 5.783 bits per weight. The nominal rate for Q5_K is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

5.40 GiB · 1 file
llama.cpp
llama-cli -hf legraphista/aya-23-8B-IMat-GGUF:Q5_K

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

Hugging Face CLI
hf download legraphista/aya-23-8B-IMat-GGUF aya-23-8B.Q5_K.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
5.40 GiB
5.80 GB
Effective bpw
5.783
from real bytes ÷ params
Tensors
Header
GGUF metadata