MiniMax-H3 · Abiray
MiniMax-H3 Q5_K_M
This file is exactly 47,774,968,384 bytes — 44.49 GiB / 47.77 GB at an effective 11.539 bits per weight. The nominal rate for Q5_K_M is lower; mixed-precision tensors make the real figure higher, always.
From the file· 2 file(s), summed
Get it
44.49 GiB · 2 files
llama.cpp
llama-cli -hf Abiray/MiniMax-H3-GGUF:Q5_K_M
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-Q5_K_M.gguf"
This quantization is split across 2 files totalling 44.49 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
44.49 GiB
47.77 GB
Effective bpw
11.539
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata