HP announces new OmniDesk Mini Desktop PC: World’s first "AI Mini PC" with Intel Core Ultra and Thunderbolt Share

[Redaktion]

HP has introduced the new HP OmniDesk Mini Desktop PC, a compact AI-powered mini-workstation featuring Intel Core Ultra Series 3 processors and Thunderbolt Share. Designed for creators and AI developers, this ultra-small form factor PC launches in August 2026, offering advanced local AI processing and quad 4K display support to streamline hybrid workflows.

https://www.notebookcheck.net/HP-announces-new-OmniDesk-Mini-Desktop-PC-World-s-first-AI-Mini-PC-with-Intel-Core-Ultra-and-Thunderbolt-Share.1312202.0.html

[Vassili]

Dear Martin,
Would you please be so kind to point out at a specific feature which is not presented in similar minicomputers of BeeLink, MINISFORUM, and other brands on the market. Also, please justify the World First claim.

[Mark Clayton]

Well not just other manufacturers. 
I have had an HP Z2 Ultra on my desk for nearly a year. Runs 4 off 4k screens and the rest of the Spec' - superb, but of course it's AMD and probably about half the price of this one...

[Greed]

Dear Martin,
Would you please be so kind to point out at a specific feature which is not presented in similar minicomputers of BeeLink, MINISFORUM, and other brands on the market. Also, please justify the World First claim.

Shhhh, don't bother them with facts!

[NPU = iGPU = bandwidth]

dedicated NPU to accelerate AI workflows

The Ryzen 350:

Overall TOPS
    Up to 66 TOPS (I think it's 8-bit / INT8)
NPU TOPS
    Up to 50 TOPS (same)

GeForce RTX 5050 Laptop GPU: 440 AI TOPS (4-bit, scammy NGREEDIA, so it's half that -- 220 -- in 8-bit)

GeForce RTX 4050-Laptop-GPU: 194 AI TOPS (8-bit)

194/66 = ~3 times, so it's 3 times slower.

3dmark.com/search:
4050 (notebook): Average score: 8288
Ryzen AI 350' 860M iGPU: Average score: 2885

8288/2885 = ~3 times, which is the same 3 times.

-> Looks like Ryzen AI 350' NPU has to be mainly understood as its iGPU, really. An iGPU is still an ASIC, the most power efficient way. Maybe a NPU is just marketing, instead of just saying it the way NVIDIA says it ("AI TOPS", no mention of a NPU).

Which tells us that it has been all along about what I said in my previous comment ("it's all about memory size, memory bandwidth and the usually, out of it, resulting GPU performance") ;)