Llama-3.1-70B-Instruct · lmstudio-community

Llama-3.1-70B-Instruct Q3_K_M

This file is exactly 34,267,499,072 bytes — 31.91 GiB / 34.27 GB at an effective 3.886 bits per weight. The nominal rate for Q3_K_M is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summedFrom the file· 724 tensors parsed

Get it

31.91 GiB · 1 file
llama.cpp
llama-cli -hf lmstudio-community/Meta-Llama-3.1-70B-Instruct-GGUF:Q3_K_M

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

Hugging Face CLI
hf download lmstudio-community/Meta-Llama-3.1-70B-Instruct-GGUF Meta-Llama-3.1-70B-Instruct-Q3_K_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.

Repository →
Size
31.91 GiB
34.27 GB
Effective bpw
3.886
from real bytes ÷ params
Tensors
724
Header
7.87 MB
GGUF metadata

What this quantization actually contains

per-tensor types, parsed from the GGUF header
Q3_K
321
F32
162
Q4_K
155
Q5_K
85
Q6_K
1

A quantization label names a mixture, not a uniform precision. Attention and output tensors are routinely kept at higher precision than the label implies, which is exactly why the effective bits-per-weight above exceeds the nominal rate.