🔌
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 XLM-RoBERTa?
Yes — here's how fast and up to what context, with real measured numbers.
XLM-RoBERTa on the AMD Ryzen AI Max+ 395
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1718k | 146.6-179.2 t/s | ~5.7-7 (slow) |
| Q8 | yes | 1727k | 293.2-358.4 t/s | ~11.5-14 (slow) |
| Q4 | yes | 1730k | 523.6-640 t/s | ~20.5-25 (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 XLM-RoBERTa?▶
Yes. At Q4 it generates ~523.6-640 tok/s and fits up to 1730k context; beyond that it spills to SSD swap and slows to ~20.5-25 tok/s.
How much context fits?▶
At Q4, up to about 1730k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.