Mistral-Large-3-675B-Instruct-2512 Q8_0

llama-cli -hf unsloth/Mistral-Large-3-675B-Instruct-2512-GGUF:Q8_0

Downloads and runs in one step, resolving the quantization by name.

hf download unsloth/Mistral-Large-3-675B-Instruct-2512-GGUF --include "Q8_0/Mistral-Large-3-675B-Instruct-2512-Q8_0-00001-of-00015.gguf"

This quantization is split across 15 files totalling 666.53 GiB. You need every part — the first is not a smaller version of the model.

• Q8_0/Mistral-Large-3-675B-Instruct-2512-Q8_0-00001-of-00015.gguf
• Q8_0/Mistral-Large-3-675B-Instruct-2512-Q8_0-00002-of-00015.gguf
• Q8_0/Mistral-Large-3-675B-Instruct-2512-Q8_0-00003-of-00015.gguf
• Q8_0/Mistral-Large-3-675B-Instruct-2512-Q8_0-00004-of-00015.gguf
• Q8_0/Mistral-Large-3-675B-Instruct-2512-Q8_0-00005-of-00015.gguf
• Q8_0/Mistral-Large-3-675B-Instruct-2512-Q8_0-00006-of-00015.gguf
• Q8_0/Mistral-Large-3-675B-Instruct-2512-Q8_0-00007-of-00015.gguf
• Q8_0/Mistral-Large-3-675B-Instruct-2512-Q8_0-00008-of-00015.gguf
• Q8_0/Mistral-Large-3-675B-Instruct-2512-Q8_0-00009-of-00015.gguf
• Q8_0/Mistral-Large-3-675B-Instruct-2512-Q8_0-00010-of-00015.gguf
• Q8_0/Mistral-Large-3-675B-Instruct-2512-Q8_0-00011-of-00015.gguf
• Q8_0/Mistral-Large-3-675B-Instruct-2512-Q8_0-00012-of-00015.gguf
• Q8_0/Mistral-Large-3-675B-Instruct-2512-Q8_0-00013-of-00015.gguf
• Q8_0/Mistral-Large-3-675B-Instruct-2512-Q8_0-00014-of-00015.gguf
• Q8_0/Mistral-Large-3-675B-Instruct-2512-Q8_0-00015-of-00015.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.