Nvidia unveils RTX Spark chip for local AI agent and LLM execution
Nvidia, in collaboration with Microsoft, has introduced the RTX Spark chip designed for Windows PCs to run AI agents and large language models locally without cloud reliance.
Nvidia has announced the RTX Spark, a new chip for Windows PCs aimed at enabling local execution of AI agents and large language models. The project was developed in partnership with Microsoft over approximately three years.
Nvidia positions the RTX Spark as the foundation for personal AI systems that operate entirely on the user's device, eliminating the need for constant cloud connectivity. The chip offers up to 1 petaflops of compute power and up to 128 GB of unified memory.
According to Nvidia, users will be able to run agentic and generative AI models directly on their PC, bringing enterprise-level AI capabilities to personal computing environments.
Source: ForkLog