NVIDIA XR AI: Open-Source AI Agents for AR Glasses
NVIDIA released XR AI on June 16, 2026, an open-source library for building AI agents on AR glasses and XR headsets, now in public beta.
NVIDIA ACE Game Agent SDK: On-Device AI NPCs in UE5
NVIDIA released the ACE Game Agent SDK and three Unreal Engine 5 plugins that let game creators build AI NPCs running on-device on the player RTX GPU, with no cloud calls or per-message cost.
NVIDIA Nemotron 3.5 ASR: 40 Languages at 80ms Latency
NVIDIA released Nemotron 3.5 ASR on June 4: an open 600M streaming speech model covering 40 language-locales with sub-100ms latency for voice agents.
NVIDIA Nemotron 3 Ultra: 5x Speed for AI Agent Workflows
NVIDIA released Nemotron 3 Ultra on June 4, 2026, a 550B MoE model with 55B active parameters that delivers 5x faster throughput and 30% cost savings on agent tasks.
FLUX.2 Klein Ships On-Device on ASUS ProArt Laptops
Black Forest Labs ships FLUX.2 klein 4B preloaded on ASUS ProArt RTX laptops with sub-5s offline image generation on 8GB VRAM.
NVIDIA Cosmos 3: Free Physical AI Tools Launch at CVPR 2026
NVIDIA unveiled Cosmos 3 at CVPR 2026: an open physical AI foundation model paired with free vision synthesis and 3D reconstruction tools on GitHub.
NVIDIA Cosmos Coalition: Runway, BFL, LTX Join
NVIDIA forms Cosmos Coalition with Runway, Black Forest Labs, and LTX to build open video generation infrastructure.
NVIDIA PiD Adds FLUX.2 Color Fix and Qwen-Image Support
NVIDIA pushed new PiD checkpoints June 2 with a FLUX.2 color-fix variant plus Qwen-Image support, all on Apache 2.0 for direct 4K decode in ComfyUI.
NVIDIA NemoClaw: One-Command Local Agents on DGX Spark
NVIDIA shipped NemoClaw on June 1, 2026, a single-command installer for local AI agents on DGX Spark hardware, with multi-node clustering up to 512GB pooled memory.
NVIDIA JetPack 7.2 Brings Agentic AI to Jetson Edge
NVIDIA shipped JetPack 7.2 at COMPUTEX 2026 with NemoClaw agentic AI skills, CUDA 13 on Jetson Orin, and a 20% performance boost on AGX Orin 32GB reaching 241 TOPS.
Nemotron 3 Ultra: NVIDIA's 550B Open-Weights MoE
NVIDIA released Nemotron 3 Ultra on June 1 2026: a 550B mixture-of-experts model with 55B active parameters, open weights on Hugging Face, with 5x faster inference and 30% lower cost than Nemotron 2.
DGX Station for Windows: Run 1T-Param Models Locally
NVIDIA announced DGX Station for Windows at Computex 2026, putting a GB300 Grace Blackwell Ultra chip and 748GB of memory into a desktop that runs trillion-parameter models locally.
RTX Spark Superchip: 128GB Unified Memory for Creators
NVIDIA officially launched the RTX Spark Superchip at GTC Taipei on June 1, 2026, putting a 6144-CUDA-core GPU, a 20-core Grace Arm CPU, and 128GB of unified memory into a single thin-and-light PC chip.
How to Prep Adobe + Blender for NVIDIA RTX Spark in 2026
Step-by-step prep for Adobe Photoshop, Premiere Pro, Substance 3D, and Blender on the NVIDIA RTX Spark Blackwell superchip. Audit, benchmark, and plan procurement before the 2x speedup ships later in 2026.
NVIDIA Cosmos 3 Tops Open-Source Image and Video Benchmarks
NVIDIA Cosmos 3 ranks first among open-source models on the Artificial Analysis Text-to-Image leaderboard. The 64B-parameter model ships with image-to-video capability and open commercial-use weights.
Tesla V100 in a Gaming PC: 32GB Local LLM for £200
Developer Oscar Molnar installed a secondhand Tesla V100 SXM2 into his gaming PC alongside an RTX 4080, building a 32GB dual-GPU setup for under £200 total.
Nvidia Adopts OpenMDW for Cosmos and Nemotron Open Models
Nvidia is bringing Cosmos, Nemotron, GR00T, and Ising under OpenMDW-1.1. Here is what the unified AI model license means for creative AI developers.
NVIDIA Releases Qwen3.6 NVFP4: 35B Multimodal MoE in 4-bit
NVIDIA ships an NVFP4 4-bit quantized build of Qwen3.6-35B-A3B, cutting GPU memory 3x with under 1% accuracy loss on eight benchmarks.
NVIGI 1.6 Tutorial: Ship a Multilingual NPC in 30 Minutes
Ship a local multilingual NPC on RTX hardware in 30 minutes with NVIGI SDK 1.6 plus DLSS 4.5 for Unreal Engine 5. Step-by-step, troubleshooting included.
Nvidia LocateAnything: 10x Faster Vision Grounding
Nvidia released LocateAnything-3B on May 27, 2026, a vision-language model 10x faster than Qwen3-VL at object detection with SOTA accuracy on GUI grounding and document understanding.
CUDA 13.3 Ships Python 1.0 + 15% LLM Inference Boost
CUDA 13.3 lands Python 1.0 stable, CompileIQ for 15% LLM inference speedups, and PyTorch/JAX zero-copy. What creative AI builders gain.
NVIDIA Retires GeForce Control Panel After 20 Years
NVIDIA officially retired its GeForce Control Panel on May 26, 2026 after 20 years, completing the migration of all GPU settings to the NVIDIA app.
NVIDIA Nemotron Diffusion: 3x Faster LLM Decoding
NVIDIA released the Nemotron-Labs-Diffusion family on Hugging Face, an open-weights LLM that switches between autoregressive, diffusion, and self-speculation decoding for 2.7x to 3.3x throughput gains.
NVIDIA Vera CPU Lands at Anthropic, OpenAI, SpaceXAI
NVIDIA delivered the first Vera CPUs, its first chip purpose-built for agentic AI, to Anthropic, OpenAI, SpaceXAI, and Oracle on May 18, 2026. The chip targets the orchestration layer Claude, ChatGPT, and Grok run on.