Aya Expanse 8B AWQ is a quantized version of the Aya Expanse multilingual large language model. It supports 23 languages and is designed for efficient inference using the AWQ quantization method. The model is provided as open weights on Hugging Face for use with the Transformers library and compatible inference engines.
In the Foundation models & chat space, Aya Expanse 8b takes a focused approach. It focuses on running large multilingual language models efficiently on consumer hardware with reduced memory usage. Aya Expanse 8b is an open-source project aimed at developers. The project is open source (Open Source). Aya Expanse 8b is available on the web, the command line, and API.
It is developed by Orion-zhen, and it first shipped in 2024. Key capabilities include quantized weights, multilingual support, and chat template.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do