Llama-3.1-70B-Instruct · bartowski
Llama-3.1-70B-Instruct Q4_K_L
This file is exactly 43,300,194,880 bytes — 40.33 GiB / 43.30 GB at an effective 4.910 bits per weight. The nominal rate for Q4_K_L is lower; mixed-precision tensors make the real figure higher, always.
From the file· 1 file(s), summed
Get it
40.33 GiB · 1 file
llama.cpp
llama-cli -hf bartowski/Meta-Llama-3.1-70B-Instruct-GGUF:Q4_K_L
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download bartowski/Meta-Llama-3.1-70B-Instruct-GGUF Meta-Llama-3.1-70B-Instruct-Q4_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.
Size
40.33 GiB
43.30 GB
Effective bpw
4.910
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata