Mistral-Large-3-675B-Instruct-2512 · unsloth
Mistral-Large-3-675B-Instruct-2512 UD-IQ2_XXS
This file is exactly 224,807,238,656 bytes — 209.37 GiB / 224.81 GB at an effective 2.671 bits per weight. The nominal rate for UD-IQ2_XXS is lower; mixed-precision tensors make the real figure higher, always.
From the file· 5 file(s), summed
Get it
209.37 GiB · 5 files
llama.cpp
llama-cli -hf unsloth/Mistral-Large-3-675B-Instruct-2512-GGUF:UD-IQ2_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-IQ2_XXS/Mistral-Large-3-675B-Instruct-2512-UD-IQ2_XXS-*-of-*.gguf"
This quantization is split across 5 files totalling 209.37 GiB. You need every part — the first is not a smaller version of the model.
Direct downloads — all 5 required
- UD-IQ2_XXS/Mistral-Large-3-675B-Instruct-2512-UD-IQ2_XXS-00001-of-00005.gguf
- UD-IQ2_XXS/Mistral-Large-3-675B-Instruct-2512-UD-IQ2_XXS-00002-of-00005.gguf
- UD-IQ2_XXS/Mistral-Large-3-675B-Instruct-2512-UD-IQ2_XXS-00003-of-00005.gguf
- UD-IQ2_XXS/Mistral-Large-3-675B-Instruct-2512-UD-IQ2_XXS-00004-of-00005.gguf
- UD-IQ2_XXS/Mistral-Large-3-675B-Instruct-2512-UD-IQ2_XXS-00005-of-00005.gguf
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
209.37 GiB
224.81 GB
Effective bpw
2.671
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata