Mistral-Large-3-675B-Instruct-2512 UD-IQ3_XXS

This file is exactly 279,215,127,616 bytes — 260.04 GiB / 279.22 GB at an effective 3.317 bits per weight. The nominal rate for UD-IQ3_XXS is lower; mixed-precision tensors make the real figure higher, always.

From the file· 6 file(s), summed

Get it

260.04 GiB · 6 files
llama.cpp
llama-cli -hf unsloth/Mistral-Large-3-675B-Instruct-2512-GGUF:UD-IQ3_XXS

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

Hugging Face CLI
hf download unsloth/Mistral-Large-3-675B-Instruct-2512-GGUF --include "UD-IQ3_XXS/Mistral-Large-3-675B-Instruct-2512-UD-IQ3_XXS-*-of-*.gguf"

This quantization is split across 6 files totalling 260.04 GiB. You need every part — the first is not a smaller version of the model.

Size
260.04 GiB
279.22 GB
Effective bpw
3.317
from real bytes ÷ params
Tensors
Header
GGUF metadata