Llama-Guard-3-8B · eaddario

Llama-Guard-3-8B IQ3_M

This file is exactly 3,685,259,648 bytes — 3.43 GiB / 3.69 GB at an effective 3.671 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

3.43 GiB · 1 file

llama.cpp

llama-cli -hf eaddario/Llama-Guard-3-8B-GGUF:IQ3_M

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

Hugging Face CLI

hf download eaddario/Llama-Guard-3-8B-GGUF Llama-Guard-3-8B-IQ3_M.gguf

Direct download

Llama-Guard-3-8B-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

3.43 GiB

3.69 GB

Effective bpw

3.671

from real bytes ÷ params

Tensors

—

Header

—

GGUF metadata