Mistral-Large-3-675B-Instruct-2512 IQ4_NL

This file is exactly 380,738,813,248 bytes — 354.59 GiB / 380.74 GB at an effective 4.523 bits per weight. The nominal rate for IQ4_NL is lower; mixed-precision tensors make the real figure higher, always.

From the file· 8 file(s), summed

Get it

354.59 GiB · 8 files
llama.cpp
llama-cli -hf unsloth/Mistral-Large-3-675B-Instruct-2512-GGUF:IQ4_NL

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 "IQ4_NL/Mistral-Large-3-675B-Instruct-2512-IQ4_NL-*-of-*.gguf"

This quantization is split across 8 files totalling 354.59 GiB. You need every part — the first is not a smaller version of the model.

Size
354.59 GiB
380.74 GB
Effective bpw
4.523
from real bytes ÷ params
Tensors
Header
GGUF metadata