←
AMD Ryzen5,877 posts
AMD Ryzen avatar✓

AMD Ryzen ✓

@AMDRyzen

@AMD Ryzen processors enable digital creators, VR pioneers, game world explorers and tech thrill-seekers. Need support? Visit our forum: bit.ly/AMDForum

◷ Joined August 2016▧ 2,568 Photos and videos
AMD Ryzen avatar
AMD Ryzen@AMDRyzen·Nov 13

Build bigger with AMD Ryzen AI Halo + Strata. Run larger, higher-quality Qwen and DeepSeek models locally on Windows and Linux, with a cloud-like experience that brings the latest community AI models directly to your PC. bit.ly/4xv5PJS

0:51
AMD Ryzen avatar
AMD Ryzen@AMDRyzen·Nov 13

Who is Ryzen AI Halo for? Ian Wineberg of AMD joined MTS to talk about how local AI is opening up new possibilities. 💻 Building applications, even without a traditional coding background 🔌 Running AI locally anywhere 🔐 Giving developers and businesses more ways to experiment with AI locally Watch the conversation: bit.ly/4zJY6bG

1:20
Jack Huynh avatar
⟳ AMD Ryzen retweeted
Jack Huynh@jackhuynh·Nov 11

Project Zenith is here! Built with @Microsoft, it's now available on our new Ryzen AI Halo, powered by Gorgon Halo. Less time setting up. More time building, experimenting, and bringing ideas to life. Coming soon to more @AMD powered devices. More freedom to build. More possibilities to unlock.

Post attachment
AMD Ryzen avatar
AMD Ryzen@AMDRyzen·Nov 11

Ryzen AI Halo is bringing more complex AI workloads right to the desk. 💻 See Ian Wineberg of AMD demonstrate multiple models running locally in this live demo with MTS. bit.ly/4zJY6bG

0:41
AMD Ryzen avatar
AMD Ryzen@AMDRyzen·Nov 6

Game builder as a "First Build” on a new AMD Ryzen AI Halo. We can now create all kinds of mini games with just one prompt. Our stack: VS Code, Cline, LM Studio, ComfyUI, Qwen 3.8 Flash and Qwen 3.8 27B. Cloud once, then local unlocked. Start your "First Build" now with AMD Ryzen AI Halo. bit.ly/3V5q6qZ

1:03
Donato Capitella avatar
⟳ AMD Ryzen retweeted
Donato Capitella@dcapitella·Nov 2

Why DeepSeek V4.1 1710 Feels Faster at the Same Token Speed. A model doesn’t have to generate tokens faster to finish sooner. I talk about why producing fewer thinking tokens can make a difference. Full episode: strix-halo-stars.com/episode…

0:58
AMD Ryzen avatar
AMD Ryzen@AMDRyzen·Nov 2

“Absurdly Cool” 3D Machines Built with Local AI on AMD Ryzen AI Max+ Wireframe animations created with the hot new skill, Anatomy, are generated with local models. Start building now with AMD Ryzen AI Max+ processors. developer.amd.com/playbooks

0:54
MTS avatar
⟳ AMD Ryzen retweeted
MTS@MTSlive·Oct 29

AMD's Ian Weinberg reveals how a computer the size of a book can run a 300-billion-parameter AI model locally: AMD's Ian Weinberg reveals how the new Ryzen AI Halo can run a 300-billion-parameter AI model locally on a computer the size of a book: "Inside of it is our next generation Ryzen AI Max+ Pro 495 processor." "The headline feature of the 495 is 192 gigs of shared RAM between the CPU and the GPU. When you look at developers today doing local AI, what they run out of very often is memory. It’s not the compute side, it’s the memory side." "Of that 192, you can reserve 160 of it for dedicated GPU VRAM, and that unlocks 300 billion parameter models that can be run local. Like GLM 5.3 Flash can be run directly on this box." "A 300 billion parameter model runs on a box that is basically the size of a book. Less than two inches tall." @AMD

Post attachment
2:10
MTS avatar
⟳ AMD Ryzen retweeted
MTS@MTSlive·Oct 29

AMD's Ian Weinberg gives a live demo of the Ryzen AI Halo running multiple massive AI models simultaneously on a computer the size of a book: "This is the Qwen 3.8 Flash Next, about 120 billion traditional parameters plus another 56 or so of n-grams. It made a song for me, and I don’t love it. So, make it more like dancehall Robyn with a slower beat." @AMD

Post attachment
3:39
AMD Ryzen avatar
AMD Ryzen@AMDRyzen·Oct 22

Live research with local models using the new Perplexity Portable Computer. We are building a local-first, personalized AI news priority feed running on the Perplexity PPLX 27B. Building new possibilities on AMD Ryzen AI Max+ architecture. bit.ly/4khjBvc

0:40
AMD Ryzen avatar
AMD Ryzen@AMDRyzen·Oct 22

Picture an AI that reads your files to answer any question instantly, powered by a dedicated chip that doesn't waste your CPU or GPU resources. That's local AI done right.

1:34
AMD Ryzen avatar
AMD Ryzen@AMDRyzen·Oct 19

Your agent should be available whenever you need it, without forcing software engineers to jump between applications. With dedicated AI hardware, workflows stay seamless (and entirely on device). Make efficiency feel like magic.

1:11
AMD Ryzen avatar
AMD Ryzen@AMDRyzen·Oct 16

A lot of workstation in 3.08 pounds. 💻 StorageReview found the Dell Pro Precision 5 14s with AMD Ryzen AI 9 HX PRO 475 especially strong in CPU-heavy workloads, delivering serious workstation performance in a highly portable design. Read more: storagereview.com/review/del…

AMD Ryzen avatar
AMD Ryzen@AMDRyzen·Oct 16

One small but punchy Ornith 1.5 9B model runs our local desktop research team, using browsers to find fresh ideas for new game builds. Powered by Hermes, LM Studio, and 128GB AMD Ryzen AI Max+ unified memory. See how AMD is helping builders build.

0:51
AMD Ryzen avatar
AMD Ryzen@AMDRyzen·Oct 15

Why keep paying for AI compute you can run yourself? A Lenovo Legion powered by AMD Ryzen AI Max+ can run useful AI models locally—handling repeat workflows offline and without per-request API fees.

1:11