🔌
New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
// RUN — FITS
Can the AMD Ryzen AI Max+ 395 run base LM+GNN+kNN?
Yes — here's how fast and up to what context, with real measured numbers.
base LM+GNN+kNN on the AMD Ryzen AI Max+ 395
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1727k | 294.3-359.7 t/s | ~11.5-14.1 (slow) |
| Q8 | yes | 1731k | 588.6-719.4 t/s | ~23-28.1 (slow) |
| Q4 | yes | 1733k | 1051.1-1284.7 t/s | ~41.1-50.2 (slow) |
Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.
FAQ
Can the AMD Ryzen AI Max+ 395 run base LM+GNN+kNN?▶
Yes. At Q4 it generates ~1051.1-1284.7 tok/s and fits up to 1733k context; beyond that it spills to SSD swap and slows to ~41.1-50.2 tok/s.
How much context fits?▶
At Q4, up to about 1733k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.