EXAONE-3.5-32B-Instruct-AWQ is an instruction-tuned 32 billion parameter model developed by LG AI Research. It supports both English and Korean and is provided in 4-bit AWQ quantized format for efficient local inference. The model is designed for conversational tasks and general text generation.
EXAONE 3.5 32B Instruct is a Foundation models & chat project. It focuses on running a high-performance, multilingual instruction model locally with reduced memory footprint via AWQ quantization. It is built as an open-source project for developers. EXAONE 3.5 32B Instruct is open source under the Open Source license. It runs on the web and the command line.
LG AI Research builds and maintains EXAONE 3.5 32B Instruct, and it first shipped in 2024. Among its 3 catalogued features are Instruction Tuning, 4-bit Quantization, and Multilingual Support.
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