Llama-Guard-3-8B · legraphista

Llama-Guard-3-8B IQ3_XXS

This file is exactly 3,274,913,600 bytes — 3.05 GiB / 3.27 GB at an effective 3.263 bits per weight. The nominal rate for IQ3_XXS is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

3.05 GiB · 1 file

llama.cpp

llama-cli -hf legraphista/Llama-Guard-3-8B-IMat-GGUF:IQ3_XXS

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

Hugging Face CLI

hf download legraphista/Llama-Guard-3-8B-IMat-GGUF Llama-Guard-3-8B.IQ3_XXS.gguf

Direct download

Llama-Guard-3-8B.IQ3_XXS.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

3.05 GiB

3.27 GB

Effective bpw

3.263

from real bytes ÷ params

Tensors

—

Header

—

GGUF metadata