JetBrains Junie Local integrates with NVIDIA RTX Spark

JetBrains has announced that its local AI coding tool, Junie Local, is now compatible with the NVIDIA RTX Spark platform from day one. Additionally, support for Windows has transitioned from an experimental phase to a stable release.

Junie Local functions as an agentic AI coding assistant that can read code, edit files, and run tests directly on a user's machine. Because the tool runs locally, it requires no registration, does not charge token fees, has no usage quotas, and ensures that code remains on the device rather than being uploaded to the cloud.

On the NVIDIA RTX Spark platform, which utilizes Blackwell RTX GPUs and Grace CPUs, Junie Local has demonstrated generation speeds of up to 55 tokens per second. The tool is designed to automatically adjust its context window based on available GPU memory, allowing it to retain more code and conversation history. Hardware requirements for running the tool include NVIDIA RTX graphics cards with at least 24GB of VRAM, such as the RTX 3090, 4090, or 5090, running on Windows 11.