Llama-3.1-70B-Instruct IQ3_M

This file is exactly 31,937,038,912 bytes — 29.74 GiB / 31.94 GB at an effective 3.621 bits per weight. The nominal rate for IQ3_M is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

29.74 GiB · 1 file
llama.cpp
llama-cli -hf bartowski/Meta-Llama-3.1-70B-Instruct-GGUF:IQ3_M

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-IQ3_M.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
29.74 GiB
31.94 GB
Effective bpw
3.621
from real bytes ÷ params
Tensors
Header
GGUF metadata