Mistral-Large-3-675B-Instruct-2512 IQ2_XS

This file is exactly 189,541,563,520 bytes — 176.52 GiB / 189.54 GB at an effective 2.252 bits per weight. The nominal rate for IQ2_XS is lower; mixed-precision tensors make the real figure higher, always.

From the file· 5 file(s), summed

Get it

176.52 GiB · 5 files
llama.cpp
llama-cli -hf bartowski/mistralai_Mistral-Large-3-675B-Instruct-2512-GGUF:IQ2_XS

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

Hugging Face CLI
hf download bartowski/mistralai_Mistral-Large-3-675B-Instruct-2512-GGUF --include "mistralai_Mistral-Large-3-675B-Instruct-2512-IQ2_XS/mistralai_Mistral-Large-3-675B-Instruct-2512-IQ2_XS-*-of-*.gguf"

This quantization is split across 5 files totalling 176.52 GiB. You need every part — the first is not a smaller version of the model.

Direct downloads — all 5 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
176.52 GiB
189.54 GB
Effective bpw
2.252
from real bytes ÷ params
Tensors
Header
GGUF metadata