Mistral-Large-3-675B-Instruct-2512 Q4_0

This file is exactly 381,700,357,440 bytes — 355.49 GiB / 381.70 GB at an effective 4.535 bits per weight. The nominal rate for Q4_0 is lower; mixed-precision tensors make the real figure higher, always.

From the file· 8 file(s), summed

Get it

355.49 GiB · 8 files
llama.cpp
llama-cli -hf unsloth/Mistral-Large-3-675B-Instruct-2512-GGUF:Q4_0

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 "Q4_0/Mistral-Large-3-675B-Instruct-2512-Q4_0-*-of-*.gguf"

This quantization is split across 8 files totalling 355.49 GiB. You need every part — the first is not a smaller version of the model.

Size
355.49 GiB
381.70 GB
Effective bpw
4.535
from real bytes ÷ params
Tensors
Header
GGUF metadata