🔌
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 TinyBert?
Yes — here's how fast and up to what context, with real measured numbers.
TinyBert on the AMD Ryzen AI Max+ 395
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1733k | 1203.6-1471 t/s | ~47-57.5 (slow) |
| Q8 | yes | 1734k | 2407.2-2942.1 t/s | ~94-114.9 (slow) |
| Q4 | yes | 1734k | 4298.5-5253.7 t/s | ~167.9-205.2 (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 TinyBert?▶
Yes. At Q4 it generates ~4298.5-5253.7 tok/s and fits up to 1734k context; beyond that it spills to SSD swap and slows to ~167.9-205.2 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.