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

Mistral-Large-3-675B-Instruct-2512 IQ2_S

This file is exactly 190,766,333,056 bytes — 177.66 GiB / 190.77 GB at an effective 2.266 bits per weight. The nominal rate for IQ2_S is lower; mixed-precision tensors make the real figure higher, always.

From the file· 5 file(s), summed

Get it

177.66 GiB · 5 files
llama.cpp
llama-cli -hf bartowski/mistralai_Mistral-Large-3-675B-Instruct-2512-GGUF:IQ2_S

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_S/mistralai_Mistral-Large-3-675B-Instruct-2512-IQ2_S-*-of-*.gguf"

This quantization is split across 5 files totalling 177.66 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.

Repository →
Size
177.66 GiB
190.77 GB
Effective bpw
2.266
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata