AIKAR-4-omni-unquantized · mradermacher

AIKAR-4-omni-unquantized Q4_K_M

This file is exactly 7,381,378,400 bytes — 6.87 GiB / 7.38 GB at an effective 4.959 bits per weight. The nominal rate for Q4_K_M is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

6.87 GiB · 1 file

llama.cpp

llama-cli -hf mradermacher/AIKAR-4-omni-unquantized-GGUF:Q4_K_M

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

Hugging Face CLI

hf download mradermacher/AIKAR-4-omni-unquantized-GGUF AIKAR-4-omni-unquantized.Q4_K_M.gguf

Direct download

AIKAR-4-omni-unquantized.Q4_K_M.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.

Repository →

Size

6.87 GiB

7.38 GB

Effective bpw

4.959

from real bytes ÷ params

Tensors

—

Header

—

GGUF metadata