NVIDIA AI PC
@NVIDIA_AI_PC
NVIDIA Powers the World's AI. And Yours with RTX AI PCs. 💻🚀 #AIonRTX
Hey there! 👋 Welcome to the new NVIDIA AI PC channel! 💻 Whether you are deep into AI or just a little curious, we're here to explore the power of AI on your local PC. Follow along for the latest news, tech, and AI inspiration. 🚀
FLUX.2 Dev FP8 from NVIDIA is available for both Comfy Cloud and local Comfy, reducing the VRAM requirements by 50% down to 15GB! Thanks for the great support!
FLUX.2 just dropped and we've teamed up with @bfl_ml + @ComfyUI to optimize performance on RTX AI PCs. 🖼️🔥 Get started today in the #RTXAIGarage blog: nvda.ws/49AIeOk
FLUX.2 is now open-sourced and live in ComfyUI on Day 0！ 4MP photorealism, professional lighting/skin/fabric detail, enhanced text rendering, and 10-ref consistency. Available on Comfy Cloud & local: - FLUX.2 Dev: BF16 / FP8 partnered with @NVIDIA_AI_PC - FLUX.2 Pro API: via…
FLUX.2 just dropped and we've teamed up with @bfl_ml + @ComfyUI to optimize performance on RTX AI PCs. 🖼️🔥 Get started today in the #RTXAIGarage blog: nvda.ws/49AIeOk
'Tis the season for deals. 🎁❄️ Check out holiday deals at @BestBuy on NVIDIA GeForce RTX AI PCs 👉 nvda.ws/4odBCJa
I got this little supercomputer from my friends @nvidia @NVIDIAGeForce What’s the first thing I should do with it?
With RTX 😉
DeepSeek OCR from @deepseek_ai now runs in GGUF on @nvidia RTX GPUs locally with one line of code. NexaSDK is the only engine that runs this GGUF build out of the box nexa infer NexaAI/DeepSeek-OCR-GGUF No more setup headaches. It’s the same local engine you already use for…
🚨 𝗟𝗮𝘀𝘁 𝗰𝗵𝗮𝗻𝗰𝗲! 🚨 The Project G-Assist Plug-in Hackathon for Home Control ends today at 11:59pm Pacific Time. Finalize your plug-in, record your demo, and hit submit before the deadline — for a shot at winning a GeForce RTX 5090/5080/5070 GPU: nvda.ws/3LuqvOG
Hyperlink, your on-device AI super assistant for files, just got way faster. Our local AI agent is optimized to run on @nvidia RTX AI PCs — accelerating search indexing by up to 3x and LLM responses by up to 2x. Learn more in @NVIDIA_AI_PC's #RTXAIGarage blog👉…
Meet Hyperlink, the first AI super assistant that lives inside your computer. Your computer stores all your files and personal context. Hyperlink deeply understands them and gives cited answers instantly — like Perplexity for your local files. It turns your computer into a true…
Your local AI agent, upgraded. @Nexa_ai's Hyperlink is accelerated by RTX AI PCs allowing for scans of gigabytes of local files in minutes — fast, private, and all on your device. Get started today #RTXAIGarage 👉 nvda.ws/3LSZDYA
𝟯 𝗱𝗮𝘆𝘀 𝗹𝗲𝗳𝘁 to build your dream AI home assistant! 🧠 The Project G-Assist Plug-in Hackathon for Home Control ends Thursday, 11/13. Submit your plug-in for a chance to win prizes like a RTX 5090 GPU ➡️ nvda.ws/4nRvruv
.@LMStudio just got faster on RTX GPUs. 🚀 Flash Attention is now enabled by default — up to ~10% speed boost, no menu diving required.
🚨 One week to go in our NVIDIA Project G-Assist Home Control Hackathon! 🚨 Register today, then submit your home control themed plug-in. You could win an RTX 5090 GPU 👉 nvda.ws/4oW8qay
Congratulations @ggerganov on the launch of WebUI for llama.cpp! 🎉
The new WebUI in combination with the advanced backend capabilities of llama.cpp delivers the ultimate local AI chat experience It's fast, private, free and open-source It runs on any hardware - today Huge thanks to the team at @huggingface for initiating, leading and…
Hundreds of creators at #AdobeMAX. One RTX-powered masterpiece. Watch the #MadeWithRTX community-edited music video. 📺 Huge thanks to everyone who helped bring it to life. 💚
📣 Our Project G-Assist #AIonRTXHackathon ends November 13th! 📣 Submit a G-Assist plug-in for home control for a chance to win a GeForce RTX 50 Series GPU. 🏆 Get started today ➡️ nvda.ws/4hBLxa2
We teamed up with @NVIDIA to teach you how to fine-tune LLMs on Blackwell & RTX 50 GPUs. Unsloth makes training on Blackwell up to 2× faster with 70% less VRAM - no accuracy loss. Learn how to use our new Docker image & more in the official NVIDIA Blog: developer.nvidia.com/blog/train-an-…
Bring high-accuracy and efficient models to RTX AI PCs with @UnslothAI Now with Quantization-Aware Training, use less VRAM while maintaining accuracy and improving performance.
You can now quantize LLMs to 4-bit and recover 70% accuracy via Quantization-Aware Training. We teamed up with @PyTorch to show how QAT enables: • 4x less VRAM with no inference overhead • 1-3% increase in raw accuracy (GPQA, MMLU Pro) Notebook & Blog: docs.unsloth.ai/new/quantizati…
NVIDIA CEO Jensen Huang is delivering a live keynote in Washington, D.C. for the first time at #NVIDIAGTC 🌎 Join us as he shares what’s next in agentic AI, robotics, and accelerated computing. Watch Now: nvda.ws/47eachm
There’s still time to catch the excitement ✨ Don’t miss the iconic interviews happening now at #NVIDIAGTC Live in Washington D.C.! Tune in now: nvda.ws/4qDSPyb
United States Trends
- 1. Happy Thanksgiving Eve 3,438 posts
- 2. Good Wednesday 27K posts
- 3. #wednesdaymotivation 4,322 posts
- 4. #Wednesdayvibe 2,127 posts
- 5. Colorado State 3,114 posts
- 6. Nuns 7,273 posts
- 7. Mora 22K posts
- 8. Hump Day 10.3K posts
- 9. Stranger Things Day 2,973 posts
- 10. Happy Hump 6,845 posts
- 11. Luka 68.6K posts
- 12. Hong Kong 52K posts
- 13. Karoline Leavitt 25K posts
- 14. Clippers 19.9K posts
- 15. Tina Turner 4,912 posts
- 16. El Salvador 47.7K posts
- 17. The God 421K posts
- 18. Collar 46.9K posts
- 19. Joy Reid 4,653 posts
- 20. Bayern 89.3K posts
Something went wrong.
Something went wrong.