Llama-Guard-3-8B · eaddario

Llama-Guard-3-8B Q6_K

This file is exactly 6,568,008,064 bytes — 6.12 GiB / 6.57 GB at an effective 6.543 bits per weight. The nominal rate for Q6_K is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

6.12 GiB · 1 file

llama.cpp

llama-cli -hf eaddario/Llama-Guard-3-8B-GGUF:Q6_K

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-Q6_K.gguf

Direct download

Llama-Guard-3-8B-Q6_K.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

6.12 GiB

6.57 GB

Effective bpw

6.543

from real bytes ÷ params

Tensors

—

Header

—

GGUF metadata