Mistral-Large-3-675B-Instruct-2512 · unsloth
Mistral-Large-3-675B-Instruct-2512 Q6_K
This file is exactly 553,317,879,616 bytes — 515.32 GiB / 553.32 GB at an effective 6.573 bits per weight. The nominal rate for Q6_K is lower; mixed-precision tensors make the real figure higher, always.
From the file· 12 file(s), summed
Get it
515.32 GiB · 12 files
llama.cpp
llama-cli -hf unsloth/Mistral-Large-3-675B-Instruct-2512-GGUF:Q6_K
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 "Q6_K/Mistral-Large-3-675B-Instruct-2512-Q6_K-00001-of-00012.gguf"
This quantization is split across 12 files totalling 515.32 GiB. You need every part — the first is not a smaller version of the model.
Direct downloads — all 12 required
- Q6_K/Mistral-Large-3-675B-Instruct-2512-Q6_K-00001-of-00012.gguf
- Q6_K/Mistral-Large-3-675B-Instruct-2512-Q6_K-00002-of-00012.gguf
- Q6_K/Mistral-Large-3-675B-Instruct-2512-Q6_K-00003-of-00012.gguf
- Q6_K/Mistral-Large-3-675B-Instruct-2512-Q6_K-00004-of-00012.gguf
- Q6_K/Mistral-Large-3-675B-Instruct-2512-Q6_K-00005-of-00012.gguf
- Q6_K/Mistral-Large-3-675B-Instruct-2512-Q6_K-00006-of-00012.gguf
- Q6_K/Mistral-Large-3-675B-Instruct-2512-Q6_K-00007-of-00012.gguf
- Q6_K/Mistral-Large-3-675B-Instruct-2512-Q6_K-00008-of-00012.gguf
- Q6_K/Mistral-Large-3-675B-Instruct-2512-Q6_K-00009-of-00012.gguf
- Q6_K/Mistral-Large-3-675B-Instruct-2512-Q6_K-00010-of-00012.gguf
- Q6_K/Mistral-Large-3-675B-Instruct-2512-Q6_K-00011-of-00012.gguf
- Q6_K/Mistral-Large-3-675B-Instruct-2512-Q6_K-00012-of-00012.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
515.32 GiB
553.32 GB
Effective bpw
6.573
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata