Product Information
What is Instella?
Instella is a state-of-the-art family of open language models trained by the AMD Genai team on AMD Instinct MI300X GPUs. The Instella models significantly outperform existing fully open language models of similar size and bridge the gap between fully open and open-weight models by achieving competitive performance compared to the Llama-3.2-3B and Qwen2.5-3B models. We provide model weights, training code, and training data to accelerate the development of open-source language models.
How to use Instella?
Instella is a series of advanced open-source language models trained by the AMD GenAI team on AMD Instinct MI300X GPUs, designed to deliver high performance and accelerate the development of open-source language models.
Core Functions of Instella
AI-driven, supercharged
AI-Driven
AMD
AI-driven, AMD
Usage Scenarios of Instella
- Accelerate the development of open-source language models.
- Serve as a high-performance open-source language model for AI research and applications.
- Use for benchmarking and comparing language model performance.
Common Questions about Instella
What does Instella do?
How do I use Instella?
What are the core features of Instella?
What are the application scenarios for Instella?




















