Pixtral-12B-2409 · EnlistedGhost

Pixtral-12B-2409 IQ3_M

This file is exactly 5,724,607,648 bytes — 5.33 GiB / 5.72 GB at an effective 3.739 bits per weight. The nominal rate for IQ3_M is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

5.33 GiB · 1 file

llama.cpp

llama-cli -hf EnlistedGhost/Pixtral-12B-2409-GGUF:IQ3_M

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

Hugging Face CLI

hf download EnlistedGhost/Pixtral-12B-2409-GGUF Pixtral-12B-2409-IQ3_M.gguf

Direct download

Pixtral-12B-2409-IQ3_M.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

5.33 GiB

5.72 GB

Effective bpw

3.739

from real bytes ÷ params

Tensors

—

Header

—

GGUF metadata