EVA-Qwen2.5-32B-v0.2-AWQ-Int4 is a community-quantized version of an enhanced Qwen2.5 32B model using AWQ 4-bit quantization. It enables efficient local inference of a powerful language model on consumer hardware. The model is hosted on Hugging Face and supports standard Transformers pipelines.
EVA Qwen2.5 32B sits in PulseGate's Foundation models & chat category. It focuses on running large 32B parameter language models locally with reduced memory requirements. EVA Qwen2.5 32B is an open-source project aimed at developers. EVA Qwen2.5 32B is open source under the Open Source license. It runs on the web and the command line, and it can be self-hosted.
Behind EVA Qwen2.5 32B is thaddeusk, and it first shipped in 2025. Among its 4 catalogued features are large language model, 4-bit quantization, and AWQ optimization.
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