Mistral-Large-3-675B-Instruct-2512 Q2_K_L

This file is exactly 247,330,266,208 bytes — 230.34 GiB / 247.33 GB at an effective 2.938 bits per weight. The nominal rate for Q2_K_L is lower; mixed-precision tensors make the real figure higher, always.

From the file· 6 file(s), summed

Get it

230.34 GiB · 6 files
llama.cpp
llama-cli -hf unsloth/Mistral-Large-3-675B-Instruct-2512-GGUF:Q2_K_L

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 "Q2_K_L/Mistral-Large-3-675B-Instruct-2512-Q2_K_L-*-of-*.gguf"

This quantization is split across 6 files totalling 230.34 GiB. You need every part — the first is not a smaller version of the model.

Size
230.34 GiB
247.33 GB
Effective bpw
2.938
from real bytes ÷ params
Tensors
Header
GGUF metadata