EXAONE
Local LLM models support English, Korean and Spanish, with reasoning and tool use, an on-device variant, and GGUF, GPTQ and AWQ formats.
EXAONE is a family of language models from LG AI Research for developers building multilingual AI applications on their own hardware. It combines everyday language tasks with reasoning for harder problems and supports agents that call external tools.
- Reasoning modes: Both models offer reasoning and non-reasoning modes, so applications can use the same model for general responses and more complex problem solving.
- Multilingual support: The models work in English, Korean and Spanish, with evaluations that include practical and professional Korean knowledge.
- Tool use: Developers can build agents that call external functions as part of a task.
- Model sizes: The 32B model targets higher performance, while the smaller 1.2B model is designed for on-device applications.
EXAONE works with Hugging Face Transformers. Quantized weights are available through Hugging Face in GGUF, GPTQ and AWQ formats, giving developers a choice of formats for local deployment.
Logotyper
