This is meta-llama/Llama-3.3-70B-Instruct 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 the quantization process and how to use the model here: How to Quantize and Run Llama 3.3 70B Instruct on Your GPU

Llama 3.3 70B Instruct_ Zero-Shot MMLU (Accuracy).png

Developed by: The Kaitchup
Language(s) (NLP): English
License: Llama 3.3

kaitchup/Llama-3.3-70B-Instruct-AutoRound-GPTQ-4bit

Model Details

kaitchup/
Llama-3.3-70B-Instruct-AutoRound-GPTQ-4bit