GPU comparison
MacBook Pro M5 Pro (24GB) 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 64 tracked models each one can run.
| MacBook Pro M5 Pro (24GB) | AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) | |
|---|---|---|
| Memory | 24.0 GB | 128.0 GB |
| Bandwidth | 307 GB/s | 256 GB/s |
| Price (approx) | $2,199 | $2,999 |
| LLMs it runs | 45 of 64 | 57 of 64 |
| Best model it runs | Qwen3.8 27B · 14–21 tok/s | Qwen3.8 Flash Next (MoE) · 45–67 tok/s |
The AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) runs 12 more of the tracked models (57 vs 45), thanks to its 128.0 GB of memory. The MacBook Pro M5 Pro (24GB) has more memory bandwidth (307 GB/s), so it generates tokens faster at the same model and quant.