MiniMax-H3 · unsloth
MiniMax-H3 Q8_0
This file is exactly 42,851,788,992 bytes — 39.91 GiB / 42.85 GB at an effective 10.350 bits per weight. The nominal rate for Q8_0 is lower; mixed-precision tensors make the real figure higher, always.
From the file· 2 file(s), summed
Get it
39.91 GiB · 2 files
llama.cpp
llama-cli -hf unsloth/MiniMax-H3-GGUF:Q8_0
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-Q8_0.gguf"
This quantization is split across 2 files totalling 39.91 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
39.91 GiB
42.85 GB
Effective bpw
10.350
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata