For-Her-Darkside-26B-A4B-v1.4 Q4_K_M

This file is exactly 34,462,874,560 bytes — 32.10 GiB / 34.46 GB at an effective 10.387 bits per weight. The nominal rate for Q4_K_M is lower; mixed-precision tensors make the real figure higher, always.

From the file· 2 file(s), summed

Get it

32.10 GiB · 2 files
llama.cpp
llama-cli -hf ReadyArt/For-Her-Darkside-26B-A4B-v1.4-GGUF:Q4_K_M

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

Hugging Face CLI
hf download ReadyArt/For-Her-Darkside-26B-A4B-v1.4-GGUF --include "For-Her-Darkside-26B-A4B-v1.4-HB16-Q4_K_M.gguf"

This quantization is split across 2 files totalling 32.10 GiB. You need every part — the first is not a smaller version of the model.

Direct downloads — all 2 required

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
32.10 GiB
34.46 GB
Effective bpw
10.387
from real bytes ÷ params
Tensors
Header
GGUF metadata