MiniMax-H3 · unsloth
MiniMax-H3 Q4_K_M
This file is exactly 18,218,065,024 bytes — 16.97 GiB / 18.22 GB at an effective 4.400 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
16.97 GiB · 1 file
llama.cpp
llama-cli -hf unsloth/MiniMax-H3-GGUF:Q4_K_M
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download unsloth/MiniMax-H3-GGUF qwen3vl_32b_minimax_h3-Q4_K_M.gguf
Direct download
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
16.97 GiB
18.22 GB
Effective bpw
4.400
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata