GPU comparison
AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) vs NVIDIA RTX Pro 6000 Blackwell (96GB) 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.
| AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) | NVIDIA RTX Pro 6000 Blackwell (96GB) | |
|---|---|---|
| Memory | 128.0 GB | 96.0 GB |
| Bandwidth | 256 GB/s | 1792 GB/s |
| Price (approx) | $2,999 | $12,999 |
| LLMs it runs | 57 of 64 | 57 of 64 |
| Best model it runs | Qwen3.8 Flash Next (MoE) · 45–67 tok/s | Qwen3.8 Flash Next (MoE) · 205–307 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 NVIDIA RTX Pro 6000 Blackwell (96GB) has more memory bandwidth (1792 GB/s), so it generates tokens faster at the same model and quant.