Harmonic-Hermes-9B · mradermacher
Harmonic-Hermes-9B I1-Q5_K_M
This file is exactly 6,467,970,720 bytes — 6.02 GiB / 6.47 GB at an effective 5.779 bits per weight. The nominal rate for I1-Q5_K_M is lower; mixed-precision tensors make the real figure higher, always.
From the file· 1 file(s), summed
Get it
6.02 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/Harmonic-Hermes-9B-i1-GGUF:I1-Q5_K_M
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download mradermacher/Harmonic-Hermes-9B-i1-GGUF Harmonic-Hermes-9B.i1-Q5_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.
Size
6.02 GiB
6.47 GB
Effective bpw
5.779
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata