Mistral-Large-3-675B-Instruct-2512 · bartowski

Mistral-Large-3-675B-Instruct-2512 IQ1_M

This file is exactly 148,492,663,776 bytes — 138.29 GiB / 148.49 GB at an effective 1.764 bits per weight. The nominal rate for IQ1_M is lower; mixed-precision tensors make the real figure higher, always.

From the file· 4 file(s), summed

Get it

138.29 GiB · 4 files

llama.cpp

llama-cli -hf bartowski/mistralai_Mistral-Large-3-675B-Instruct-2512-GGUF:IQ1_M

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

Hugging Face CLI

hf download bartowski/mistralai_Mistral-Large-3-675B-Instruct-2512-GGUF --include "mistralai_Mistral-Large-3-675B-Instruct-2512-IQ1_M/mistralai_Mistral-Large-3-675B-Instruct-2512-IQ1_M-*-of-*.gguf"

This quantization is split across 4 files totalling 138.29 GiB. You need every part — the first is not a smaller version of the model.

Direct downloads — all 4 required

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.

Repository →

Size

138.29 GiB

148.49 GB

Effective bpw

1.764

from real bytes ÷ params

Tensors

—

Header

—

GGUF metadata