AMD Strix Halo

What hackers pick instead

• Apple Mac miniA small, fast, power-efficient Mac whose unified memory suits local AI models and always-on macOS work, though storage upgrades are costly and it struggles with big LLMs.390recommend
• NVIDIA DGX SparkA quiet, compact 128GB box with fast prompt processing for running large models locally, fine-tuning and keeping data private, though its low memory bandwidth slows token generation.170recommend
• Framework DesktopA compact, low-power mini PC with up to 128GB of shared memory for running large local AI models on Linux, though critics say memory bandwidth limits LLM speed.93recommend
• Intel NUCSmall, quiet, cheap mini PC people use for home servers and basic desktop work, with replaceable RAM and storage. Critics say some models overheat.42recommend
• Beelink mini PCSmall mini PCs that run Linux or Windows well, stay quiet and cool, and last for years. People also praise the support and the value for the money.24recommend

Every quote

The 40 most detailed of 313 comments. Each links to the original.

1. Granted, I am happy with my 128gb of shared memory, but I am mildly concerned that it actually is more expensive now than when I bought mine.

   Mixed · Jun 2026 · in “AI Coding at Home Without Going Broke”

2. I have had an impossible time getting 120B or better models running on Strix Halo (especially under Windows) with any large context windows.

   Mixed · Aug 2026 · in “Qwen 3.8-Flash-Next releasing tomorrow (125B a6B)”

3. Strix Halo has a wider memory bus and so it's a good way to get lots of high-bandwidth shared system/video RAM for relatively cheap.

   Recommends · Apr 2026 · in “GLM-5.1: Towards Long-Horizon Tasks”

4. being able to handle and extent context is why it'll continue to be a great machine compared to any of the small graphics cards

   Recommends · Jul 2026 · in “AMD Ryzen AI Halo – $4k AI Dev Kit”

5. the latter is pretty much always better for running local models because it's quite a bit faster due to higher memory bandwidth

   Mixed · Aug 2026 · in “Qwen 3.8-Flash-Next releasing tomorrow (125B a6B)”

6. This is roughly a doubling of the price compared to less than a year ago without adding any notable features, it's appalling.

   Mixed · Jul 2026 · in “AMD Ryzen AI Halo – $4k AI Dev Kit”

7. The Strix Halo has the benefit of being entirely a normal x86_64 PC that happens to also have a big chunk of unified memory.

   Recommends · Jul 2026 · in “AMD Ryzen AI Halo – $4k AI Dev Kit”

8. That's pretty accurate to what I've seen, I'd definitely recommend a smaller model for active agentic use on that hardware.

   Mixed · Jul 2026 · in “Hands-On with the AMD Ryzen AI Halo”

9. This model is far from usable on current AMD or Nvidia 128GB AI machines, IMHO, they just don't have the memory bandwidth

   Mixed · Aug 2026 · in “Qwen 3.8 27B is excellent, but it defaults to overthinking things”

10. Hardware is the exact same as what used to be available for $2K last year (and is still $1K cheaper from Chinese OEMs).

    Mixed · Jul 2026 · in “AMD Ryzen AI Halo – $4k AI Dev Kit”

11. After trying to load a 35B MoE model at 20.82 GiB in June on my Bosgame M5 (128GB), the load hung after 300 seconds

    Mixed · Aug 2026

12. you won't have to deal with NVIDIA's shit on Linux and worrying about having to use their custom kernels or Ubuntu

    Recommends · Jun 2026 · in “Qwen 3.6 27B is the sweet spot for local development”

13. memory speed is only going up by a few percent, so its still going to be slow with more than a few B active params

    Mixed · Aug 2026 · in “Apple caught off guard by AI demand for Mac Mini and Mac Studio”

14. Even if you believe it'll be completely obsolete for AI in two years, it'll still be good for many other things.

    Recommends · Jun 2026 · in “Unsloth GLM-5.2 – How to Run Locally”

15. This makes the $1800 I paid for my Strix Halo motherboard (128G), almost a year ago, look like a real bargain!

    Recommends · Sep 2026 · in “Framework Desktop with 192GB RAM”

16. the 128GB Strix Halo is capable if you use LLMs as assistants, but it's not so good if you use LLMs as agents

    Mixed · Jul 2026 · in “Hands-On with the AMD Ryzen AI Halo”

17. It definitely wasn't an "out of the box" experience, fiddling around with kernel versions and ROCm installs.

    Mixed · Jul 2026 · in “Nvidia DGX Spark as a daily driver”

18. The device was not perfect by any means, but the ability to run fairly large models is some kind of magic.

    Mixed · Jun 2026 · in “AMD Strix Halo RDMA Cluster Setup Guide”

19. it was an awesome machine that could do a little bit of everything, fit in a backpack and only needed 140W

    Mixed · Jun 2026 · in “AMD Strix Halo RDMA Cluster Setup Guide”

20. It becomes a pretty great desktop computer that also happens to run AI pretty well at a pretty good price.

    Recommends · Aug 2026 · in “Qwen 3.8-Flash-Next releasing tomorrow (125B a6B)”

21. So the HALO is pretty unique (outside of Apple) for providing twice the memory bandwidth of anything else

    Recommends · Apr 2026 · in “My first impressions on the ROCm and Strix Halo”

22. what most of them lack compared to Strix Halo is a 128 GB pool of unified LPDDR5x-8000 on a 256 bit bus

    Recommends · Apr 2026 · in “Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model”

23. if you're looking for a general purpose computer that's also solid at AI, the AMD machine is better

    Recommends · Jul 2026 · in “AMD Ryzen AI Halo – $4k AI Dev Kit”

24. Anyone who didn’t buy a 128GB Strix Halo system when they were 2500€ has only themselves to blame.

    Recommends · Oct 2026 · in “From the creator of Redis; run LLM locally with ds4”

25. it does make this approach make more sense as a budget solution to running larger models locally

    Recommends · Jul 2026 · in “AMD Ryzen AI Halo – $4k AI Dev Kit”

26. Mac doesn't run Linux so in my books is a worse general purpose computer than a Strix Halo box.

    Recommends · Feb 2026 · in “How do I cancel my ChatGPT subscription?”

27. Strix Halo at $2k with similar TG and about half the PP of DGX Spark was a pretty good deal IMO

    Recommends · May 2026 · in “Qwen3.7-Max: The Agent Frontier”

28. The unified memory architecture is what makes Strix Halo interesting for inference workloads.

    Recommends · Apr 2026 · in “My first impressions on the ROCm and Strix Halo”

29. you’re not getting access to more than 48GB of fast memory without something similar to this

    Mixed · Jul 2026 · in “AMD Ryzen AI Halo – $4k AI Dev Kit”

30. reasons why you should keep your carveout small on Strix Halo on AMD's ROCm

    Mixed · Aug 2026

31. if you are serious about it and you have Strix Halo, there are better ways of getting more context and capability and speed

    Criticizes · Sep 2026 · in “Notes on gotchas while migrating 35kb preprompts from Opus to self-hosted Ollama”

32. AMD is still a pain point. Many tools and libraries don't have first class AMD support or any support at all.

    Criticizes · Jul 2026 · in “AMD Ryzen AI Halo – $4k AI Dev Kit”

33. It's neither high bandwidth, nor does it have CUDA support, nor does it have support from the big OEMs.

    Criticizes · Jun 2026 · in “Qwen 3.6 27B is the sweet spot for local development”

34. If you're asking for something closer to the RTX Spark or Apple Silicon then look at AMD's Strix Halo systems.

    Recommends · Jun 2026 · in “Nvidia is proposing a beast of a CPU system for Windows PCs”

35. And now Strix Halo, which were it not for DDR5 prices shooting to the moon, would be incredible prosumer APU.

    Recommends · Nov 2025 · in “AMD continues to chip away at Intel's x86 market share”

36. Strix Halo is supported in ROCm 6.x, so it should be supported on most platforms (I haven't tested it tho).

    Mixed · Mar 2026 · in “Nvidia greenboost: transparently extend GPU VRAM using system RAM/NVMe”

37. the only reason I would recommend against them is if you plan on getting multiple to link together

    Mixed · Jul 2026 · in “AMD Ryzen AI Halo – $4k AI Dev Kit”

38. i wish there was a system like strix halo, but with enough lanes for a dedicated PCIe 5.0 x16 slot

    Mixed · Jul 2026 · in “AMD Ryzen AI Halo – $4k AI Dev Kit”

39. People are similarly using the AMD Strix Halo for AI which also has a similar memory architecture.

    Recommends · Jan 2026 · in “Kimi Released Kimi K2.5, Open-Source Visual SOTA-Agentic Model”

40. the added benefit that I can also pair the strix halo with an egpu to drastically speed things up

    Recommends · Sep 2026 · in “CUDA for AMD on Windows”