Llama-3.1-70B-Instruct · bartowski
Llama-3.1-70B-Instruct Q5_K_L
This file is exactly 50,598,284,032 bytes — 47.12 GiB / 50.60 GB at an effective 5.737 bits per weight. The nominal rate for Q5_K_L is lower; mixed-precision tensors make the real figure higher, always.
From the file· 2 file(s), summed
Get it
47.12 GiB · 2 files
llama.cpp
llama-cli -hf bartowski/Meta-Llama-3.1-70B-Instruct-GGUF:Q5_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 --include "Meta-Llama-3.1-70B-Instruct-Q5_K_L/Meta-Llama-3.1-70B-Instruct-Q5_K_L-*-of-*.gguf"
This quantization is split across 2 files totalling 47.12 GiB. You need every part — the first is not a smaller version of the model.
Direct downloads — all 2 required
- Meta-Llama-3.1-70B-Instruct-Q5_K_L/Meta-Llama-3.1-70B-Instruct-Q5_K_L-00001-of-00002.gguf
- Meta-Llama-3.1-70B-Instruct-Q5_K_L/Meta-Llama-3.1-70B-Instruct-Q5_K_L-00002-of-00002.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.
Size
47.12 GiB
50.60 GB
Effective bpw
5.737
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata