Hardware comparison
AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) vs NVIDIA DGX Spark (GB10, 128GB) for local LLMs
How the two stack up for running open-source LLMs locally — memory, bandwidth, price, and how many of the 69 tracked models each one can run.
Scroll sideways to compare both machines. Keyboard: focus the table, then use the arrow keys. Metric names stay visible.
| Hardware | AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) | NVIDIA DGX Spark (GB10, 128GB) |
|---|---|---|
| Memory | 128.0 GB | 128.0 GB |
| Bandwidth | 256 GB/s | 273 GB/s (better for this comparison) |
| Price (approx) | $2,999 (better for this comparison)Complete system | $4,699Complete system |
| LLMs it runs | 62 of 69 | 62 of 69 |
| Best model it runs | Gemma 4 31BQ2_K · estimated 12–19 tok/s | Gemma 4 31BQ2_K · estimated 13–20 tok/s |
Both prices cover complete systems. Prices are approximate catalog estimates; check current configurations and prices before buying.
Both estimated speeds use the same model and quant shown above. Estimates use 4,096 context tokens, llama.cpp and one stream.
The AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) and NVIDIA DGX Spark (GB10, 128GB) run the same number of tracked models. Compare their ecosystem and purchase scope before price. The NVIDIA DGX Spark (GB10, 128GB) has more memory bandwidth (273 GB/s). Higher bandwidth can help generation speed, but model, quant, architecture and runtime also affect the estimates.