shieldgemma-27b · mradermacher

shieldgemma-27b Q8_0

This file is exactly 28,937,388,672 bytes — 26.95 GiB / 28.94 GB at an effective 8.502 bits per weight. The nominal rate for Q8_0 is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

26.95 GiB · 1 file

llama.cpp

llama-cli -hf mradermacher/shieldgemma-27b-GGUF:Q8_0

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

Hugging Face CLI

hf download mradermacher/shieldgemma-27b-GGUF shieldgemma-27b.Q8_0.gguf

Direct download

shieldgemma-27b.Q8_0.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

26.95 GiB

28.94 GB

Effective bpw

8.502

from real bytes ÷ params

Tensors

—

Header

—

GGUF metadata