The #NVIDIARTXPRO platform for professional visualization drives the innovation of graphics and #AI, from the desktop to the data center to the cloud.
Joined November 2009
- Tweets 8,706
- Following 1,142
- Followers 36,771
- Likes 3,012
2,141 Photos and videos
One open model. 350,000 motion clips. 15,000 FPS.
MotionBricks from NVIDIA Research runs real-time character animation at scale, without hand-crafted transitions or fine-tuning. And yes, it works for robotics too.
#SIGGRAPH2026 paper, demos code: nvlabs.github.io/motionbrick…
36
130
1,107
105,364
Congrats to @GoogleDeepMind on the launch of DiffusionGemma.
The model generates 256 tokens in parallel per step, delivering 150 TPS on DGX Spark, and 1,000 TPS on a single H100.
We're supporting it from day one with:
• BF16 and NVFP4 checkpoints on @huggingface🤗
• Free GPU-accelerated endpoints on build.nvidia.com
• @vllm_project support with FP8 precision
Get started with DiffusionGemma on NVIDIA: nvda.ws/43ro19u
DiffusionGemma, our experimental open model released under an Apache 2.0 license, explores text diffusion, an exceptionally fast approach to text generation.
Here’s how DiffusionGemma accelerates development:
Faster token output: By shifting the bottleneck from memory bandwidth to raw compute, the model generates up to 4x faster token output on dedicated GPUs
Accessible hardware footprint: Activates just 3.8B parameters during inference, fitting comfortably within 24GB-VRAM high-end consumer GPUs when quantized
Novel workflows: Parallel token generation enables self-correction, making it ideal for code infilling, in-line editing, and non-linear structures
DiffusionGemma prioritizes speed over raw quality and accelerates best on compute-bound hardware (like @NVIDIAAI GPUs). Standard @GoogleGemma 4 remains recommended for production quality and memory-bound devices.
38
118
1,366
99,093
We will be there. 👀
See you in L.A.👉 nvda.ws/4wM8G0x
May 16
Still thinking about attending SIGGRAPH 2026?
Find out what everyone will be using next year before they even know it exists.
From emerging research to production-ready breakthroughs, this is where new tools, techniques, and ideas are first revealed across graphics, AI, and immersive technology.
Don’t miss what’s unfolding. Check out the schedule as more sessions continue to be released. s2026.conference-schedule.or…
14
17
151
48,325
Awesome to see @vu_studio using NVIDIA DGX Spark to power faster, smarter, and more interactive workflows — including impactful work with Moffitt Cancer Center 👏
May 20
Real-time visualization hits different when it’s faster than real time.
We worked with @NVIDIAworkstatn to turn ideas, conversations, and data into instant visuals powered by NVIDIA DGX Spark and our semantic media engine.
Read more here: vu.studio/news/dgx-spark
@MoffittNews
1
6
908
NVIDIA Workstation retweeted
Apr 30
Get more control over outputs in @ComfyUI.
We've released new workflows that can help accelerate concepting & storyboarding while maintaining creative control. 👇
1
7
23
2,258
Nemotron 3 Nano Omni is here — and it runs locally on NVIDIA RTX PRO. 🖥️ Full multimodal AI on your workstation.
Meet Nemotron 3 Nano Omni 👋
Our latest addition to the Nemotron family is the highest efficiency, open multimodal model with leading accuracy.
30B parameters. 256K context length. 🧵👇
1
5
670
NVIDIA Workstation retweeted
Apr 17
Here's your weekend project. Build a fully local, sandboxed AI assistant.
Step-by-step tutorial to build your always-on agent:
🦞 on @openclaw
✅ with NVIDIA NemoClaw
✨ using NVIDIA DGX Spark
Get started: developer.nvidia.com/blog/bu…
35
84
645
41,477
NVIDIA Workstation retweeted
Apr 15
No more jumping between apps for color work.
@AdobeVideo Premiere's new Color Mode keeps editors in their creative flow with RTX GPU-accelerated grading, 32-bit color depth precision, context-aware scopes and more.
Full details 👇
1
6
28
8,009
Spatial computing is no longer tethered to a desk. 🌐
With NVIDIA CloudXR 6.0, we’re bridging the gap between high-fidelity RTX rendering and mobile XR devices.
It’s now possible to stream professional 3D apps to Apple Vision Pro and web browsers with:
✨ Universal OpenXR streaming
🔋 Improved hardware efficiency
🖥️ Zero-friction web access via CloudXR.js
Learn how to get started: nvda.ws/4ckxljs
5
9
152
35,717
The future of edge robotics is local, private, and exceptionally fast. 🤖
HP, NVIDIA, and Hugging Face teamed up to build a fully local medical triage AI agent leveraging the HP ZGX Nano and the Pollen Robotics Reachy Mini that achieves sub-2.5-second latency without ever touching the cloud.
✨ Read the blog: nvda.ws/4vm338B
1
3
7
600
NVIDIA CloudXR.js is here.✨🥽
Our new JavaScript SDK lets you stream high-fidelity, GPU-rendered XR content directly to any standard web browser.
Whether it's an NVIDIA Omniverse digital twin or a robot simulation in Isaac Lab, we're making professional XR as accessible as a webpage.
Get the details: nvda.ws/4dmvug8
5
20
879
NVIDIA Workstation retweeted
🙌 Congrats @GoogleDeepMind and teams on the release of your @googlegemma 4 models!🎉
The new multimodal and multilingual models are built for fast, efficient, and secure AI across devices – and optimized to run locally on NVIDIA RTX, RTX PRO, DGX Spark, and Jetson.
👉 Prototype the 31B model and start experimenting for free on build.nvidia.com/google/gemm…
🔗Check out the details to get started in our Technical Blog: developer.nvidia.com/blog/br…
Meet Gemma 4: our new family of open models you can run on your own hardware.
Built for advanced reasoning and agentic workflows, we’re releasing them under an Apache 2.0 license. Here’s what’s new 🧵
34
126
1,082
73,262
🚀 Lightweight aerospace design meets accelerated computing.
Sintavia, working with Siemens and nTop, is redefining thermal engineering and accelerating aerospace design with the NVIDIA RTX PRO 6000 Blackwell Workstation Edition.
The result? Over 11x faster simulation cycles, rapid design iteration, and a fully optimized aerospace heat exchanger delivered in just two weeks.
Learn more ➡️ nvda.ws/3PWVRiU
1
12
662
Announced at GTC: NVIDIA Partners Unveil New NVIDIA RTX PRO Blackwell-Based Workstations 🔥
Run demanding AI workloads faster and more efficiently with new systems from Lenovo, Dell, and HP—powered by NVIDIA RTX PRO Blackwell GPUs.
Read the blog: blogs.nvidia.com/blog/gtc-20…
1
12
570
NVIDIA Workstation retweeted
Mar 18
A surprise from Kia at an NVIDIA event.
Amid a vibrant showcase of next-generation technologies, the dynamic Kia Vision Meta Turismo appeared in XR at the GPU Technology Conference, standing out as a bold, progressive innovation born from global collaboration.
#Kia #KiaVisionMetaTurismo #MovementThatInspires
1
9
37
2,385
NVIDIA Workstation retweeted
Mar 17
🦞 Thanks to everyone who stopped by at Build-a-Claw yesterday.
You can BYOD or purchase a DGX Spark there and engineers will help you install and answer any questions about @OpenClaw.
📆 Reminder - open each day of #NVIDIAGTC at 8am, until 5 p.m. Tues/Wed and until 2 p.m. Thurs.
📍 GTC Park
🔗 nvidia.com/gtc/training/buil…
28
36
285
45,814
Don't miss the latest in XR and spatial computing at GTC. Get the details here:
✨ Complete XR sessions agenda
🎮 10 immersive demo experiences
🎤 Featured talks from Apple, Stanford, McLaren & more
🔗 Learn more about the latest technologies
👉 nvda.ws/3Pe3Vvs
3
19
688
Big news for spatial computing. 🥽
NVIDIA RTX-accelerated computers now connect directly to Apple Vision Pro with NVIDIA CloudXR 6.0 for visionOS, bringing real-time, photorealistic 3D streaming for design, simulation, and immersive apps.
🔗 Learn more: blogs.nvidia.com/blog/nvidia…
1
28
212
11,884
NVIDIA Workstation retweeted
Mar 16
NVIDIA DGX Station is now available to order from select OEMs🔥
Powered by the GB300 Grace Blackwell Ultra Desktop Superchip, DGX Station brings data-center-class AI performance to the desk — enabling developers to build and run autonomous AI agents locally.
⚡ 748GB of coherent memory
⚡ Up to 20 petaflops of AI compute performance
⚡ Run large open models up to one trillion parameters
Together with NVIDIA NemoClaw — an open source stack that simplifies running OpenClaw always-on assistants, more safely, with a single command, we are delivering a full-stack platform for secure, long-running agentic AI.
Learn more: blogs.nvidia.com/blog/gtc-20…
116
149
1,419
241,270
Extended reality is set to revolutionize the hands-on workforce ⚡
At GTC 2026, learn how AI agents can deliver real-time guidance to boost worker productivity and safety, powered by NVIDIA, Ramblr, Convai, AWS and GridRaster.
📅 Wednesday, March 18 | 4:00 p.m. - 4:40 p.m. PDT
🔗: nvda.ws/3PuOnDx
1
5
513