Side-by-side simulation · recommended settings
Ryzen AI Max+ 395 vs DGX Spark: Which 128GB local LLM machine?
Both list 128GB, but GPU allocation and software environments differ. Decide between an AMD path on Windows or Linux and an NVIDIA CUDA server before comparing.
Choose devices and a model
Expand comparison settings
Same 117output tokens. Only evidence-qualified acceleration is selected automatically; runtime formats are shown on each device.
Left
ReadyRyzen AI Max+ 395 128GB
Press Start above to generate the same answer on both devices.
Right
ReadyDGX Spark 128GB
Press Start above to generate the same answer on both devices.
With these settings, Ryzen AI Max+ 395 128GB finishes the full answer About 1.9× faster.
Compare from input processing to completion of 117 token response.
Which one fits my needs?
Answer completion
Ryzen AI Max+ 395 128GB
At the estimate midpoint, it finishes the same answer about 1.9× faster.
Prompt processing
Ryzen AI Max+ 395 128GB
The estimated input-processing midpoint is higher at 1,265 tok/s.
Image and video generation
Check the media model
LLM speed does not tell you media-generation performance. Choose the image or video model and resolution separately.
Runtime
Settings for your hardware
Strata 0.1.40 · IQ3_S · ROCm 7.14.1 · MTP-4 / llama.cpp · Q4_K_M. When runtime paths differ, the speed gap also includes software and model-format differences.
Estimated power draw
Ryzen AI Max+ 395 128GB
Estimated LLM power draw is lower at about 125 W. Noise and physical size need a separate check.
Local pricing
While Ryzen AI Max+ 395 128GB is about 441 × KRW 10,000 cheaper, this model's response is also faster.
Before choosing hardware
| Measure | Ryzen AI Max+ 395 128GB | DGX Spark 128GB |
|---|---|---|
| Available fast memory | 96GB | 116GB |
| Memory bandwidth | 256GB/s | 273GB/s |
| Estimated total time | 5.2 s | 9.8 s |
| Estimated sustained LLM load | about 125W | about 190W |
| Korean price range (KRW) | 538–562 × KRW 10,000 | 952–1,030 × KRW 10,000 |
Estimated ranges for one user. Multi-GPU and multi-device results depend on the runtime and interconnect.
Start with the memory available to the GPU
On a Ryzen AI Max+ system, check both GPU allocation and memory left for the OS. DGX Spark also needs operating-system and runtime headroom. Compare loading using the usable-memory figures below and check whether the actual machine's BIOS and OS can use that allocation.
Choose between AMD runtimes and CUDA tools
To keep CUDA-only packages, examine the Spark environment. On AMD, select the ROCm, Vulkan or HIP path actually supported by the system and tool. If you have a specific tool in mind, its OS, architecture and package support table matters before the GPU name.
Keep prices tied to the actual chassis
Ryzen AI Max+ 395 machines vary in memory, SSD and cooling. GB10-family products also vary by vendor. Match the memory option and actual chassis to this comparison when checking prices. A different chassis also calls for checking power and sustained execution conditions.