Mistral-Large-3-675B-Instruct-2512 · bartowski

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

This file is exactly 269,619,903,808 bytes — 251.10 GiB / 269.62 GB at an effective 3.203 bits per weight. The nominal rate for IQ3_XXS is lower; mixed-precision tensors make the real figure higher, always.

From the file· 7 file(s), summed

Get it

251.10 GiB · 7 files
llama.cpp
llama-cli -hf bartowski/mistralai_Mistral-Large-3-675B-Instruct-2512-GGUF:IQ3_XXS

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-IQ3_XXS/mistralai_Mistral-Large-3-675B-Instruct-2512-IQ3_XXS-*-of-*.gguf"

This quantization is split across 7 files totalling 251.10 GiB. You need every part — the first is not a smaller version of the model.

Direct downloads — all 7 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
251.10 GiB
269.62 GB
Effective bpw
3.203
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata