Key facts
- Nvidia has unveiled its Blackwell AI chip.
- The Blackwell chip promises enhanced performance and efficiency for AI computing.
- It is designed for demanding AI workloads like large language models and simulations.
- The chip is expected to accelerate AI development across industries.
Nvidia has officially launched its next-generation AI chip, codenamed Blackwell. This new architecture is set to redefine the landscape of artificial intelligence computing, offering a significant leap in performance and efficiency compared to its predecessors. Blackwell is engineered to tackle the most computationally intensive AI tasks, including the training and deployment of massive large language models (LLMs) and intricate scientific simulations. Nvidia claims that systems powered by Blackwell could deliver up to a 100x performance increase for certain AI workloads. The company also highlighted the chip's ability to handle AI models with up to 400 billion parameters. Nvidia anticipates that Blackwell-powered systems will begin to become available in 2025, further solidifying the company's dominance in the AI hardware market.