Ryzen AI MAX+ 395 LLM benchmark
No Ryzen AI MAX+ 395 LLM benchmarks yet. Be the first to submit a signed, reproducible tok/s run from your own Ryzen AI MAX+ 395.
Will it run local LLMs?
No signed Ryzen AI MAX+ 395 run yet, but its 96GB of VRAM tells you what fits. At 4-bit it comfortably runs models up to about 99B parameters with room for context, and up to roughly 157B with tighter quantization. Check a specific model with the VRAM-fit tool.
No Ryzen AI MAX+ 395 benchmarks yet.
Run on YOUR hardware to populate this page: pipx install llm-speed && llm-speed bench
$ pipx install llm-speed && llm-speed bench
Common questions about Ryzen AI MAX+ 395
Direct Q&A drawn from the runs above: fastest LLM, supported model classes, backend rankings, quantization guidance.