NVIDIA expands local agent computing with RTX PCs and DGX Spark

NVIDIA used GTC to highlight new open models, local agent software, and fine-tuning tools aimed at running agentic Artificial Intelligence workloads on RTX PCs and DGX Spark. The announcements focus on privacy, lower operating costs, and better local performance for personal assistants and creative applications.

NVIDIA is positioning RTX PCs and DGX Spark as systems for running personal agents locally, with an emphasis on private, always-on assistants that can access personal files, apps, and workflows without relying on cloud inference. At GTC, the company highlighted a set of updates spanning open models, an open source OpenClaw stack, and simplified fine-tuning tools designed to make local agent deployment more practical for developers and enthusiasts.

The new model lineup centers on local inference across NVIDIA hardware. DGX Spark is described as especially suited to larger agentic workloads, with its 128GB of unified memory that supports models with more than 120 billion parameters. Nemotron 3 Super is a 120-billion-parameter open model with 12 billion active parameters, designed to run complex agentic Artificial Intelligence systems. On PinchBench, Nemotron 3 Super scored 85.6%, making it the top open model in its class. Mistral Small 4, a 119-billion-parameter open model with 6 billion active parameters, 8 billion including all layers, is positioned for general chat, coding and agentic tasks. For smaller systems, Nemotron 3 Nano 4B targets GeForce RTX users building local assistants and conversational personas on constrained hardware. NVIDIA also announced optimizations for Alibaba’s Qwen 3.5 models, including 27B, 9B and 4B. The new models natively support vision, multi-token prediction and a large 262,000-token context window. The dense 27-billion-parameter model excels when paired with an RTX 5090 GPU.

NVIDIA also introduced NemoClaw, an open source stack for OpenClaw that brings NVIDIA-specific optimizations to local agents. The initial release includes NVIDIA Nemotron open models and the NVIDIA OpenShell runtime. NVIDIA says local inference through Nemotron models improves privacy and eliminates token costs, while OpenShell is designed to execute claws more safely. At the same time, the company promoted a hands-on build-a-claw event running through March 19, from 8 a.m.-5 p.m., where attendees can configure and deploy a proactive assistant on their device of choice.

Beyond agents, NVIDIA highlighted RTX-optimized creative and model-tuning tools. LTX 2.3 now supports NVFP4 and FP8 distilled models, accelerating performance by 2.1x. FLUX.2 Klein 9B received an update that accelerates image editing by up to 2x, alongside a new FP8 version optimized for RTX GPUs. Unsloth Studio launched as a web-based interface for fine-tuning, with support for more than 500 AI models. Built on the Unsloth library, it delivers up to 2x faster training with up to 70% VRAM savings, giving RTX GPU and DGX Spark users a simpler path to customizing local models for agentic workflows.

60

Impact Score

Snap speeds Snapchat A/B testing with NVIDIA data libraries

Snap has moved key Snapchat experimentation workloads to NVIDIA-accelerated Apache Spark on Google Cloud, aiming to process large daily data volumes faster and at lower cost. The shift supports broader feature testing across engagement, performance and monetization metrics.

NVIDIA RTX systems connect to Apple Vision Pro

NVIDIA and Apple are bringing native integration of NVIDIA CloudXR 6.0 to visionOS. The move enables secure streaming of NVIDIA RTX-powered simulators and professional 3D graphics applications to Apple Vision Pro.

OpenAI’s Pentagon access and xAI’s Grok lawsuit lead the day

OpenAI’s decision to give the Pentagon access to its Artificial Intelligence is raising questions about how quickly generative systems could move into military operations. Meanwhile, xAI is facing a lawsuit alleging Grok enabled the creation of child sexual abuse material.

Contact Us

Got questions? Use the form to contact us.

Contact Form

Clicking next sends a verification code to your email. After verifying, you can enter your message.