redponike's picture
Create README.md
ce7cd07 verified
metadata
base_model:
  - nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1

GGUF quants of nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1

Using llama.cpp b5436 (commit be0239693c1530a18496086331fc18d8a9adbad1)

The importance matrix was generated with calibration_datav3.txt.

All quants were generated/calibrated with the imatrix, including the K quants.

Quantized from BF16.