Llama-3.1-8B-Instruct-heretic · bartowski

Llama-3.1-8B-Instruct-heretic Q6_K_L

This file is exactly 6,850,471,904 bytes — 6.38 GiB / 6.85 GB at an effective 6.825 bits per weight. The nominal rate for Q6_K_L is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

6.38 GiB · 1 file
llama.cpp
llama-cli -hf bartowski/p-e-w_Llama-3.1-8B-Instruct-heretic-GGUF:Q6_K_L

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

Hugging Face CLI
hf download bartowski/p-e-w_Llama-3.1-8B-Instruct-heretic-GGUF p-e-w_Llama-3.1-8B-Instruct-heretic-Q6_K_L.gguf
Direct download

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
6.38 GiB
6.85 GB
Effective bpw
6.825
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata