Mistral-Large-Instruct-2407 · InferenceIllusionist
Mistral-Large-Instruct-2407 IQ3_S
This file is exactly 52,996,917,152 bytes — 49.36 GiB / 53.00 GB at an effective 3.458 bits per weight. The nominal rate for IQ3_S is lower; mixed-precision tensors make the real figure higher, always.
From the file· 2 file(s), summed
Get it
49.36 GiB · 2 files
llama.cpp
llama-cli -hf InferenceIllusionist/Mistral-Large-Instruct-2407-iMat-GGUF:IQ3_S
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_S-*-of-*.gguf"
This quantization is split across 2 files totalling 49.36 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_S-00001-of-00002.gguf
- Mistral-Large-Instruct-2407-iMat-IQ3_S-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
49.36 GiB
53.00 GB
Effective bpw
3.458
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata