This is meta-llama/Meta-Llama-3.1-8B quantized with AutoRound (symmetric quantization) and serialized with the GPTQ format in 4-bit. The model has been created, tested, and evaluated by The Kaitchup.

Details on quantization process, evaluation, and how to use the model here: The Best Quantization Methods to Run Llama 3.1 on Your GPU

Developed by: The Kaitchup
Language(s) (NLP): English
License: cc-by-4.0

kaitchup/Meta-Llama-3.1-8B-autoround-gptq-4bit-sym

Model Details

kaitchup/
Meta-Llama-3.1-8B-autoround-gptq-4bit-sym