🔌
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 BiRNA-BERT?
Yes — here's how fast and up to what context, with real measured numbers.
BiRNA-BERT on the AMD Ryzen AI Max+ 395
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1731k | 689.2-842.4 t/s | ~26.9-32.9 (slow) |
| Q8 | yes | 1733k | 1378.5-1684.8 t/s | ~53.8-65.8 (slow) |
| Q4 | yes | 1734k | 2461.5-3008.5 t/s | ~96.2-117.5 (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 BiRNA-BERT?▶
Yes. At Q4 it generates ~2461.5-3008.5 tok/s and fits up to 1734k context; beyond that it spills to SSD swap and slows to ~96.2-117.5 tok/s.
How much context fits?▶
At Q4, up to about 1734k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.