Meta-Llama-3.2-3B · NousResearch
Meta-Llama-3.2-3B Q6_K
This file is exactly 2,643,850,048 bytes — 2.46 GiB / 2.64 GB at an effective 6.583 bits per weight. The nominal rate for Q6_K is lower; mixed-precision tensors make the real figure higher, always.
From the file· 1 file(s), summed
Get it
2.46 GiB · 1 file
llama.cpp
llama-cli -hf NousResearch/Hermes-3-Llama-3.2-3B-GGUF:Q6_K
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download NousResearch/Hermes-3-Llama-3.2-3B-GGUF Hermes-3-Llama-3.2-3B.Q6_K.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
2.46 GiB
2.64 GB
Effective bpw
6.583
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata