Overview
Luxia is Saltlux's GPT-based large language model trained on one of the largest proprietary Korean corpora, designed specifically for Korean NLP tasks. Unlike conventional models, Luxia features incremental learning and an optimized fine-tuning system that enables domain-specific adaptation with high efficiency. With enhanced control mechanisms, it significantly reduces hallucinations and delivers more accurate and trustworthy text generation. When integrated with Saltlux's enterprise-grade search solution, Luxia can fully leverage Retrieval-Augmented Generation (RAG) to generate more context-aware and reliable responses. This combination minimizes hallucinations and improves generation quality across use cases such as document Q&A, semantic search, and intelligent assistants.
Highlights
- GPT-based large language model optimized for Korean natural language understanding and generation
- Supports incremental learning and advanced fine-tuning for domain-specific adaptation
- Enables effective use of RAG techniques to enhance response accuracy and reliability
Details
Unlock automation with AI agent solutions

Features and programs
Financing for AWS Marketplace purchases
Pricing
Vendor refund policy
This is a BYOL (Bring Your Own License) product. As such, no software charges are applied through AWS Marketplace.
No refunds will be issued. For technical support, contact cloud-koreaseller@saltlux.com .
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
64-bit (x86) Amazon Machine Image (AMI)
Amazon Machine Image (AMI)
An AMI is a virtual image that provides the information required to launch an instance. Amazon EC2 (Elastic Compute Cloud) instances are virtual servers on which you can run your applications and workloads, offering varying combinations of CPU, memory, storage, and networking resources. You can launch as many instances from as many different AMIs as you need.
Version release notes
Initial release of the Luxia2-8b product on AWS Marketplace.
This version includes:
- Luxia 8B language model integrated with the vLLM inference engine
- Optimized for g6.xlarge instance type with NVIDIA L4 GPU
- API service container and Gradio-based frontend interface
This is the first version made publicly available.
Additional details
Usage instructions
- Launch the instance using the recommended g6.xlarge instance type.
- The Luxia Chat API will be available at http://<public-ip>:15006/docs
- The web UI will be accessible at http://<public-ip>:15003
- Please note that it may take at least 20 minutes for all services to fully start after the instance is launched.
Support
Vendor support
For technical support, please contact us at cloud-koreaseller@saltlux.com Our support team is available from 9 AM to 6 PM (KST), Monday to Friday. We provide assistance with installation, model integration, and usage guidance.
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.