Mistral-Large-3-675B-Instruct-2512 IQ2_M

This file is exactly 216,213,306,592 bytes — 201.36 GiB / 216.21 GB at an effective 2.568 bits per weight. The nominal rate for IQ2_M is lower; mixed-precision tensors make the real figure higher, always.

From the file· 6 file(s), summed

Get it

201.36 GiB · 6 files
llama.cpp
llama-cli -hf bartowski/mistralai_Mistral-Large-3-675B-Instruct-2512-GGUF:IQ2_M

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_M/mistralai_Mistral-Large-3-675B-Instruct-2512-IQ2_M-*-of-*.gguf"

This quantization is split across 6 files totalling 201.36 GiB. You need every part — the first is not a smaller version of the model.

Direct downloads — all 6 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
201.36 GiB
216.21 GB
Effective bpw
2.568
from real bytes ÷ params
Tensors
Header
GGUF metadata