Mistral-Large-3-675B-Instruct-2512 Q3_K_M

This file is exactly 321,845,570,720 bytes — 299.74 GiB / 321.85 GB at an effective 3.823 bits per weight. The nominal rate for Q3_K_M is lower; mixed-precision tensors make the real figure higher, always.

From the file· 7 file(s), summed

Get it

299.74 GiB · 7 files
llama.cpp
llama-cli -hf unsloth/Mistral-Large-3-675B-Instruct-2512-GGUF:Q3_K_M

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 "Q3_K_M/Mistral-Large-3-675B-Instruct-2512-Q3_K_M-*-of-*.gguf"

This quantization is split across 7 files totalling 299.74 GiB. You need every part — the first is not a smaller version of the model.

Size
299.74 GiB
321.85 GB
Effective bpw
3.823
from real bytes ÷ params
Tensors
Header
GGUF metadata