Mistral-Large-Instruct-2407 · InferenceIllusionist
Mistral-Large-Instruct-2407 IQ3_XS
This file is exactly 50,142,168,960 bytes — 46.70 GiB / 50.14 GB at an effective 3.272 bits per weight. The nominal rate for IQ3_XS is lower; mixed-precision tensors make the real figure higher, always.
From the file· 2 file(s), summed
Get it
46.70 GiB · 2 files
llama.cpp
llama-cli -hf InferenceIllusionist/Mistral-Large-Instruct-2407-iMat-GGUF:IQ3_XS
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download InferenceIllusionist/Mistral-Large-Instruct-2407-iMat-GGUF --include "Mistral-Large-Instruct-2407-iMat-IQ3_XS-*-of-*.gguf"
This quantization is split across 2 files totalling 46.70 GiB. You need every part — the first is not a smaller version of the model.
Direct downloads — all 2 required
- Mistral-Large-Instruct-2407-iMat-IQ3_XS-00001-of-00002.gguf
- Mistral-Large-Instruct-2407-iMat-IQ3_XS-00002-of-00002.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
46.70 GiB
50.14 GB
Effective bpw
3.272
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata