GPU comparison
Mac Studio M3 Ultra (96GB) vs AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) for local LLMs
How the two stack up for running open-source LLMs locally — memory, bandwidth, price, and how many of the 34 tracked models each one can run.
| Mac Studio M3 Ultra (96GB) | AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) | |
|---|---|---|
| Memory | 96.0 GB | 128.0 GB |
| Bandwidth | 819 GB/s | 256 GB/s |
| Price (approx) | $5,299 | $2,999 |
| LLMs it runs | 30 of 34 | 30 of 34 |
| Best model it runs | Gemma 4 31B · 15–22 tok/s | Gemma 4 31B · 10–15 tok/s |
Both run the same number of models, but the AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) has more memory (128.0 GB), so it can hold larger models at higher quality. The Mac Studio M3 Ultra (96GB) has more memory bandwidth (819 GB/s), so it generates tokens faster at the same model and quant.