MiniMax-H3 · unsloth

MiniMax-H3 Q2_K

This file is exactly 13,402,362,048 bytes — 12.48 GiB / 13.40 GB at an effective 3.237 bits per weight. The nominal rate for Q2_K is lower; mixed-precision tensors make the real figure higher, always.

From the file· 2 file(s), summed

Get it

12.48 GiB · 2 files

llama.cpp

llama-cli -hf unsloth/MiniMax-H3-GGUF:Q2_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-Q2_K.gguf"

This quantization is split across 2 files totalling 12.48 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.

Repository →

Size

12.48 GiB

13.40 GB

Effective bpw

3.237

from real bytes ÷ params

Tensors

—

Header

—

GGUF metadata