A collection of Llama 3 models quantized by Astronomer
-
astronomer/Llama-3-8B-Instruct-GPTQ-8-Bit
Text Generation • 8B • Updated • 78 • 25 -
astronomer/Llama-3-8B-Instruct-GPTQ-4-Bit
Text Generation • 8B • Updated • 145 • 25 -
astronomer/Llama-3-8B-GPTQ-8-Bit
Text Generation • 8B • Updated • 21 • 3 -
astronomer/Llama-3-8B-GPTQ-4-Bit
Text Generation • 8B • Updated • 46 • 7