Mistral-Large-3-675B-Instruct-2512 · unsloth
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.
Direct downloads — all 8 required
- Q4_0/Mistral-Large-3-675B-Instruct-2512-Q4_0-00001-of-00008.gguf
- Q4_0/Mistral-Large-3-675B-Instruct-2512-Q4_0-00002-of-00008.gguf
- Q4_0/Mistral-Large-3-675B-Instruct-2512-Q4_0-00003-of-00008.gguf
- Q4_0/Mistral-Large-3-675B-Instruct-2512-Q4_0-00004-of-00008.gguf
- Q4_0/Mistral-Large-3-675B-Instruct-2512-Q4_0-00005-of-00008.gguf
- Q4_0/Mistral-Large-3-675B-Instruct-2512-Q4_0-00006-of-00008.gguf
- Q4_0/Mistral-Large-3-675B-Instruct-2512-Q4_0-00007-of-00008.gguf
- Q4_0/Mistral-Large-3-675B-Instruct-2512-Q4_0-00008-of-00008.gguf
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
355.49 GiB
381.70 GB
Effective bpw
4.535
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata