GPU comparison
AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) vs NVIDIA RTX 4080 (16GB) 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.
| AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) | NVIDIA RTX 4080 (16GB) | |
|---|---|---|
| Memory | 128.0 GB | 16.0 GB |
| Bandwidth | 256 GB/s | 717 GB/s |
| Price (approx) | $2,999 | $1,549 |
| LLMs it runs | 30 of 34 | 18 of 34 |
| Best model it runs | Gemma 4 31B · 10–15 tok/s | Gemma 4 26B-A4B (MoE) · 141–212 tok/s |
The AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) runs 12 more of the tracked models (30 vs 18), thanks to its 128.0 GB of memory. The NVIDIA RTX 4080 (16GB) has more memory bandwidth (717 GB/s), so it generates tokens faster at the same model and quant.