Everything Nvidia Announced at Computex 2026: From the Nemotron 3 Ultra to RTX Spark
Nvidia used Computex 2026 to announce the Nemotron 3 Ultra, its most intelligent open weights model, the RTX Spark consumer superchip for Windows PCs, and the ramp of its Vera Rubin AI factory platform—a complete hard... The Nemotron 3 Ultra is a 550 billion parameter Mixture of Experts model that scored 48 on the A...
Published byEdited with DeepSeek-V4-ProImages generated with GPT Image 1.5
Nvidia used Computex 2026 to announce the Nemotron 3 Ultra, its most intelligent open weights model, the RTX Spark consumer superchip for Windows PCs, and the ramp of its Vera Rubin AI factory platform—a complete hard...
The Nemotron 3 Ultra is a 550 billion parameter Mixture of Experts model that scored 48 on the Artificial Analysis Intelligence Index, making it the highest ranking U.S.
RTX Spark is a new Arm based system on a chip for Windows laptops and desktops, combining a 20 core CPU and a Blackwell GPU with up to 128 GB of unified memory, purpose built to run powerful AI agents locally.
What did Nvidia announce at Computex 2026, including the specifications and performance of the Nemotron 3 Ultra model, the broader NemotronA generated visual summarizing Nvidia's full-stack announcements at Computex 2026.
AI Prompt
Create a landscape editorial hero image for this Studio Global article: What did Nvidia announce at Computex 2026, including the specifications and performance of the Nemotron 3 Ultra model, the broader Nemotron. Article summary: At Computex 2026 in Taipei, Jensen Huang delivered a sweeping keynote positioning Nvidia as a complete, full-stack AI platform company — covering new open models, an agent software stack, a custom CPU, a consumer superch. Topic tags: general, documentation, general web, user generated, academic. Reference image context from search candidates: Reference image 1: visual subject "NVIDIA Computex 2026 Keynote Vera Rubin Full Stack" source context "NVIDIA Computex 2026 Keynote Live Coverage - ServeTheHome" Reference image 2: visual subject "NVIDIA Computex 2026 Keynote Nemotron 3 Ultra" source context "NVIDIA Computex 2026 Keynote Live Coverage - ServeTheHome" Style:
openai.com
At Computex 2026 in Taipei, Jensen Huang delivered a keynote that reframed Nvidia as a complete, full-stack AI platform company. The announcements spanned new open-weights models, a custom CPU, a consumer superchip, a software framework for secure AI agents, and the mass production ramp of its next-generation data center infrastructure. Here are all the key specifications, performance claims, and timelines.
Nemotron 3 Ultra: the new flagship open-weights model
The centerpiece of Nvidia’s model announcements was the Nemotron 3 Ultra, officially unveiled on June 1, 2026 . It is the largest and most capable open-weights model Nvidia has released.
Architecture: Hybrid Mamba-Transformer mixture-of-experts (MoE) with and .
Studio Global AI
Continue your research
This page includes a source-backed answer you can continue inside Studio Global.
What is the short answer to "Everything Nvidia Announced at Computex 2026: From the Nemotron 3 Ultra to RTX Spark"?
Nvidia used Computex 2026 to announce the Nemotron 3 Ultra, its most intelligent open weights model, the RTX Spark consumer superchip for Windows PCs, and the ramp of its Vera Rubin AI factory platform—a complete hard...
What are the key points to validate first?
Nvidia used Computex 2026 to announce the Nemotron 3 Ultra, its most intelligent open weights model, the RTX Spark consumer superchip for Windows PCs, and the ramp of its Vera Rubin AI factory platform—a complete hard... The Nemotron 3 Ultra is a 550 billion parameter Mixture of Experts model that scored 48 on the Artificial Analysis Intelligence Index, making it the highest ranking U.S.
What should I do next in practice?
RTX Spark is a new Arm based system on a chip for Windows laptops and desktops, combining a 20 core CPU and a Blackwell GPU with up to 128 GB of unified memory, purpose built to run powerful AI agents locally.
Everything Nvidia Announced at Computex 2026: From the Nemotron 3 Ultra to RTX Spark
Nvidia used Computex 2026 to announce the Nemotron 3 Ultra, its most intelligent open weights model, the RTX Spark consumer superchip for Windows PCs, and the ramp of its Vera Rubin AI factory platform—a complete hard... The Nemotron 3 Ultra is a 550 billion parameter Mixture of Experts model that scored 48 on the A...
Published byEdited with DeepSeek-V4-ProImages generated with GPT Image 1.5
Nvidia used Computex 2026 to announce the Nemotron 3 Ultra, its most intelligent open weights model, the RTX Spark consumer superchip for Windows PCs, and the ramp of its Vera Rubin AI factory platform—a complete hard...
The Nemotron 3 Ultra is a 550 billion parameter Mixture of Experts model that scored 48 on the Artificial Analysis Intelligence Index, making it the highest ranking U.S.
RTX Spark is a new Arm based system on a chip for Windows laptops and desktops, combining a 20 core CPU and a Blackwell GPU with up to 128 GB of unified memory, purpose built to run powerful AI agents locally.
What did Nvidia announce at Computex 2026, including the specifications and performance of the Nemotron 3 Ultra model, the broader NemotronA generated visual summarizing Nvidia's full-stack announcements at Computex 2026.
AI Prompt
Create a landscape editorial hero image for this Studio Global article: What did Nvidia announce at Computex 2026, including the specifications and performance of the Nemotron 3 Ultra model, the broader Nemotron. Article summary: At Computex 2026 in Taipei, Jensen Huang delivered a sweeping keynote positioning Nvidia as a complete, full-stack AI platform company — covering new open models, an agent software stack, a custom CPU, a consumer superch. Topic tags: general, documentation, general web, user generated, academic. Reference image context from search candidates: Reference image 1: visual subject "NVIDIA Computex 2026 Keynote Vera Rubin Full Stack" source context "NVIDIA Computex 2026 Keynote Live Coverage - ServeTheHome" Reference image 2: visual subject "NVIDIA Computex 2026 Keynote Nemotron 3 Ultra" source context "NVIDIA Computex 2026 Keynote Live Coverage - ServeTheHome" Style:
openai.com
At Computex 2026 in Taipei, Jensen Huang delivered a keynote that reframed Nvidia as a complete, full-stack AI platform company. The announcements spanned new open-weights models, a custom CPU, a consumer superchip, a software framework for secure AI agents, and the mass production ramp of its next-generation data center infrastructure. Here are all the key specifications, performance claims, and timelines.
Nemotron 3 Ultra: the new flagship open-weights model
The centerpiece of Nvidia’s model announcements was the Nemotron 3 Ultra, officially unveiled on June 1, 2026 . It is the largest and most capable open-weights model Nvidia has released.
Architecture: Hybrid Mamba-Transformer mixture-of-experts (MoE) with and .
Studio Global AI
Continue your research
This page includes a source-backed answer you can continue inside Studio Global.
What is the short answer to "Everything Nvidia Announced at Computex 2026: From the Nemotron 3 Ultra to RTX Spark"?
Nvidia used Computex 2026 to announce the Nemotron 3 Ultra, its most intelligent open weights model, the RTX Spark consumer superchip for Windows PCs, and the ramp of its Vera Rubin AI factory platform—a complete hard...
What are the key points to validate first?
Nvidia used Computex 2026 to announce the Nemotron 3 Ultra, its most intelligent open weights model, the RTX Spark consumer superchip for Windows PCs, and the ramp of its Vera Rubin AI factory platform—a complete hard... The Nemotron 3 Ultra is a 550 billion parameter Mixture of Experts model that scored 48 on the Artificial Analysis Intelligence Index, making it the highest ranking U.S.
What should I do next in practice?
RTX Spark is a new Arm based system on a chip for Windows laptops and desktops, combining a 20 core CPU and a Blackwell GPU with up to 128 GB of unified memory, purpose built to run powerful AI agents locally.
Training precision: Pre-trained using NVFP4, Nvidia's 4-bit floating point format .
Key innovations: LatentMoE, which compresses token representations to improve routing quality, and multi-token prediction (MTP) heads for faster generation .
Context window: Up to 1 million tokens.
Intelligence ranking: Scored 48 on the Artificial Analysis Intelligence Index for U.S. open-weights models, outperforming Gemma 4 31B and ranking as the most intelligent U.S. open-weights model at launch .
Efficiency: Nvidia claims 5x faster inference and approximately 30% lower cost to run than comparable open models . It also delivers more than 300 output tokens per second .
Designed for: Complex reasoning, coding, instruction following, and multi-step agentic workflows .
The broader Nemotron 3 family
Nemotron 3 Ultra sits atop a three-model family that shares the same hybrid Mamba-Transformer MoE architecture .
Model
Total Parameters
Active per Token
Highlights
Nemotron 3 Nano
~4 billion
Smallest
Optimized for local and edge inference on RTX PCs and DGX Spark
Nemotron 3 Super
120 billion
12 billion
Released March 11, 2026; scored 85.6% on PinchBench, the top open model for agentic tasks
Nemotron 3 Ultra
550 billion
55 billion
Largest model; highest U.S. open-weights intelligence score at launch
All three support up to a 1-million-token context window. The Super and Ultra variants include NVFP4 training, LatentMoE, and multi-token prediction layers .
NemoClaw and OpenShell: secure, local AI agents
First introduced at GTC 2026 in March and reiterated at Computex, NemoClaw and OpenShell form Nvidia's enterprise agent stack .
NemoClaw: An open-source, Apache 2.0-licensed reference stack built on top of OpenClaw. It installs with a single command and enables local deployment of autonomous AI agents on RTX PCs, workstations, and DGX systems—no cloud API fees, and data never leaves the device .
OpenShell: An open-source security runtime that runs AI agents in a sandboxed environment. It provides policy-based guardrails, privacy controls, and isolation for long-running agent processes, comparable to a YAML-policy-driven Docker layer for AI agents .
Together they form the Nvidia Agent Toolkit, a suite for enterprises that want to build and run autonomous AI coworkers securely on local hardware .
Vera CPU: the compute brain of the Vera Rubin platform
The Nvidia Vera CPU is a custom Arm-based processor purpose-built for orchestrating AI workloads in data centers .
Core count: 88 custom Arm cores on a monolithic die with no chiplet boundaries .
Memory bandwidth: 1.2 TB/s of LPDDR5X .
On-chip fabric: 3.6 TB/s for inter-core data movement .
Single-thread performance: 10 instructions per clock (IPC) .
Nvidia claims Vera delivers 1.8x the agentic AI performance of x86 CPUs.
The Vera CPU serves as the host processor inside Vera Rubin NVL72 rack-scale systems, where it works alongside next-generation GPUs to power AI factories .
RTX Spark: a consumer superchip for Windows PCs
RTX Spark is Nvidia’s first dedicated system-on-a-chip for consumer Windows PCs, co-developed with MediaTek and built on TSMC’s 3nm process . Jensen Huang called it “everything we’ve learned over 33 years distilled into one chip” .
CPU: 20-core Arm processor — 10 Cortex-X925 performance cores plus 10 Cortex-A725 efficiency cores, peaking at 4.1 GHz .
GPU: Blackwell RTX GPU with 6,144 CUDA cores and 5th-generation Tensor Cores with FP4 support — the same core count as a desktop GeForce RTX 5070 .
Unified memory: Up to 128 GB of LPDDR5X.
Interconnect: NVLink-C2C chip-to-chip link with up to 600 GB/s bandwidth between CPU and GPU dies .
AI performance:1 petaflop of FP4 AI compute, capable of running 120-billion-parameter large language models with 1 million tokens of context entirely on-device .
Software stack: Full CUDA support, plus compatibility with NemoClaw and OpenShell for running local AI agents .
Availability: Laptops from Dell, Microsoft, and other partners are expected in fall 2026.
Use cases: Local AI agents, rendering 90 GB 3D scenes, editing 12K 4:2:2 video, AI video generation in 4K, and gaming above 100 FPS at 1440p .
Nvidia positions RTX Spark as “the world’s first Windows PCs purpose-built for personal agents” .
Vera Rubin platform: mass production and early cloud adopters
Nvidia confirmed that the Vera Rubin platform has entered full production, with systems expected to reach partners in the second half of 2026 .
Platform scope: Six to seven co-designed chips, including the Vera CPU and next-generation GPUs, architected for rack-scale AI factories .
Full rack performance: The NVL72 configuration delivers 3.6 EFLOPS of AI compute .
Supply chain scale: More than 350 factories across 30 countries, including over 150 partners in Taiwan, are manufacturing Vera Rubin systems .
Named early cloud and service provider adopters:
Hyperscalers: Microsoft Azure, AWS, Google Cloud .
At the Computex keynote, Nvidia described Vera Rubin as the foundation of the next generation of AI factories .
Nvidia's full-stack AI platform takes shape
Taken together, Computex 2026 was the clearest demonstration yet of Nvidia’s vertical integration strategy:
Silicon: Vera CPU for the data center, RTX Spark for consumer PCs, and Vera Rubin GPUs for rack-scale compute cover the full performance spectrum from edge to cloud .
Models: The Nemotron 3 family—Nano, Super, and Ultra—provides open-weights models optimized for Nvidia hardware at every deployment tier .
Software and agents: NemoClaw, OpenShell, and the Agent Toolkit let enterprises build and deploy autonomous, secure AI agents locally using Nvidia’s own models .
Infrastructure: Vera Rubin’s mass production ramp with hyperscale and cloud partners ensures the supply chain is in place to build “AI factories” at global scale .
Jensen Huang’s keynote message was singular: Nvidia now supplies every layer of the AI stack, from silicon and open models to agent runtimes and factory-scale deployment infrastructure.
coinpedia.org
NVIDIA Launches Nemotron 3 Ultra AI Model at Computex 2026
Training precision: Pre-trained using NVFP4, Nvidia's 4-bit floating point format .
Key innovations: LatentMoE, which compresses token representations to improve routing quality, and multi-token prediction (MTP) heads for faster generation .
Context window: Up to 1 million tokens.
Intelligence ranking: Scored 48 on the Artificial Analysis Intelligence Index for U.S. open-weights models, outperforming Gemma 4 31B and ranking as the most intelligent U.S. open-weights model at launch .
Efficiency: Nvidia claims 5x faster inference and approximately 30% lower cost to run than comparable open models . It also delivers more than 300 output tokens per second .
Designed for: Complex reasoning, coding, instruction following, and multi-step agentic workflows .
The broader Nemotron 3 family
Nemotron 3 Ultra sits atop a three-model family that shares the same hybrid Mamba-Transformer MoE architecture .
Model
Total Parameters
Active per Token
Highlights
Nemotron 3 Nano
~4 billion
Smallest
Optimized for local and edge inference on RTX PCs and DGX Spark
Nemotron 3 Super
120 billion
12 billion
Released March 11, 2026; scored 85.6% on PinchBench, the top open model for agentic tasks
Nemotron 3 Ultra
550 billion
55 billion
Largest model; highest U.S. open-weights intelligence score at launch
All three support up to a 1-million-token context window. The Super and Ultra variants include NVFP4 training, LatentMoE, and multi-token prediction layers .
NemoClaw and OpenShell: secure, local AI agents
First introduced at GTC 2026 in March and reiterated at Computex, NemoClaw and OpenShell form Nvidia's enterprise agent stack .
NemoClaw: An open-source, Apache 2.0-licensed reference stack built on top of OpenClaw. It installs with a single command and enables local deployment of autonomous AI agents on RTX PCs, workstations, and DGX systems—no cloud API fees, and data never leaves the device .
OpenShell: An open-source security runtime that runs AI agents in a sandboxed environment. It provides policy-based guardrails, privacy controls, and isolation for long-running agent processes, comparable to a YAML-policy-driven Docker layer for AI agents .
Together they form the Nvidia Agent Toolkit, a suite for enterprises that want to build and run autonomous AI coworkers securely on local hardware .
Vera CPU: the compute brain of the Vera Rubin platform
The Nvidia Vera CPU is a custom Arm-based processor purpose-built for orchestrating AI workloads in data centers .
Core count: 88 custom Arm cores on a monolithic die with no chiplet boundaries .
Memory bandwidth: 1.2 TB/s of LPDDR5X .
On-chip fabric: 3.6 TB/s for inter-core data movement .
Single-thread performance: 10 instructions per clock (IPC) .
Nvidia claims Vera delivers 1.8x the agentic AI performance of x86 CPUs.
The Vera CPU serves as the host processor inside Vera Rubin NVL72 rack-scale systems, where it works alongside next-generation GPUs to power AI factories .
RTX Spark: a consumer superchip for Windows PCs
RTX Spark is Nvidia’s first dedicated system-on-a-chip for consumer Windows PCs, co-developed with MediaTek and built on TSMC’s 3nm process . Jensen Huang called it “everything we’ve learned over 33 years distilled into one chip” .
CPU: 20-core Arm processor — 10 Cortex-X925 performance cores plus 10 Cortex-A725 efficiency cores, peaking at 4.1 GHz .
GPU: Blackwell RTX GPU with 6,144 CUDA cores and 5th-generation Tensor Cores with FP4 support — the same core count as a desktop GeForce RTX 5070 .
Unified memory: Up to 128 GB of LPDDR5X.
Interconnect: NVLink-C2C chip-to-chip link with up to 600 GB/s bandwidth between CPU and GPU dies .
AI performance:1 petaflop of FP4 AI compute, capable of running 120-billion-parameter large language models with 1 million tokens of context entirely on-device .
Software stack: Full CUDA support, plus compatibility with NemoClaw and OpenShell for running local AI agents .
Availability: Laptops from Dell, Microsoft, and other partners are expected in fall 2026.
Use cases: Local AI agents, rendering 90 GB 3D scenes, editing 12K 4:2:2 video, AI video generation in 4K, and gaming above 100 FPS at 1440p .
Nvidia positions RTX Spark as “the world’s first Windows PCs purpose-built for personal agents” .
Vera Rubin platform: mass production and early cloud adopters
Nvidia confirmed that the Vera Rubin platform has entered full production, with systems expected to reach partners in the second half of 2026 .
Platform scope: Six to seven co-designed chips, including the Vera CPU and next-generation GPUs, architected for rack-scale AI factories .
Full rack performance: The NVL72 configuration delivers 3.6 EFLOPS of AI compute .
Supply chain scale: More than 350 factories across 30 countries, including over 150 partners in Taiwan, are manufacturing Vera Rubin systems .
Named early cloud and service provider adopters:
Hyperscalers: Microsoft Azure, AWS, Google Cloud .
At the Computex keynote, Nvidia described Vera Rubin as the foundation of the next generation of AI factories .
Nvidia's full-stack AI platform takes shape
Taken together, Computex 2026 was the clearest demonstration yet of Nvidia’s vertical integration strategy:
Silicon: Vera CPU for the data center, RTX Spark for consumer PCs, and Vera Rubin GPUs for rack-scale compute cover the full performance spectrum from edge to cloud .
Models: The Nemotron 3 family—Nano, Super, and Ultra—provides open-weights models optimized for Nvidia hardware at every deployment tier .
Software and agents: NemoClaw, OpenShell, and the Agent Toolkit let enterprises build and deploy autonomous, secure AI agents locally using Nvidia’s own models .
Infrastructure: Vera Rubin’s mass production ramp with hyperscale and cloud partners ensures the supply chain is in place to build “AI factories” at global scale .
Jensen Huang’s keynote message was singular: Nvidia now supplies every layer of the AI stack, from silicon and open models to agent runtimes and factory-scale deployment infrastructure.
coinpedia.org
NVIDIA Launches Nemotron 3 Ultra AI Model at Computex 2026
