MiniMax-H3 · unsloth

MiniMax-H3 Q3_K

This file is exactly 17,475,434,688 bytes — 16.28 GiB / 17.48 GB at an effective 4.221 bits per weight. The nominal rate for Q3_K is lower; mixed-precision tensors make the real figure higher, always.

From the file· 2 file(s), summed

Get it

16.28 GiB · 2 files
llama.cpp
llama-cli -hf unsloth/MiniMax-H3-GGUF:Q3_K

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

Hugging Face CLI
hf download unsloth/MiniMax-H3-GGUF --include "minimax_h3_fl2va_pruned-Q3_K.gguf"

This quantization is split across 2 files totalling 16.28 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
16.28 GiB
17.48 GB
Effective bpw
4.221
from real bytes ÷ params
Tensors
Header
GGUF metadata