Mistral-Small-3.2-24B-Instruct-2507 · TheDrummer

Mistral-Small-3.2-24B-Instruct-2507 Q5_K_M

This file is exactly 16,763,984,928 bytes — 15.61 GiB / 16.76 GB at an effective 5.689 bits per weight. The nominal rate for Q5_K_M is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

15.61 GiB · 1 file
llama.cpp
llama-cli -hf TheDrummer/Cydonia-24B-v4.2.0-GGUF:Q5_K_M

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

Hugging Face CLI
hf download TheDrummer/Cydonia-24B-v4.2.0-GGUF Cydonia-24B-v4r-Q5_K_M.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.

Repository →
Size
15.61 GiB
16.76 GB
Effective bpw
5.689
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata