Deploy an AI-powered coding assistant on DGX Spark that delivers expert CUDA-aware chat, real-time code completion, and retrieval-augmented generation grounded in authoritative GPU programming knowledge—powered by NVIDIA NIM microservices.
Inkling is a multimodal (text + image) reasoning model from Thinking Machines — a Mamba-hybrid, 256-expert Mixture-of-Experts architecture with tool use and switchable reasoning.