MiniMax-H3 · Abiray
MiniMax-H3 Q4_K_S
This file is exactly 39,706,667,584 bytes — 36.98 GiB / 39.71 GB at an effective 9.590 bits per weight. The nominal rate for Q4_K_S is lower; mixed-precision tensors make the real figure higher, always.
From the file· 2 file(s), summed
Get it
36.98 GiB · 2 files
llama.cpp
llama-cli -hf Abiray/MiniMax-H3-GGUF:Q4_K_S
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download Abiray/MiniMax-H3-GGUF --include "unet/MiniMax-H3-FL2VA-Q4_K_S.gguf"
This quantization is split across 2 files totalling 36.98 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
36.98 GiB
39.71 GB
Effective bpw
9.590
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata