🔌
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 OpenELM-270M?
Yes — here's how fast and up to what context, with real measured numbers.
OpenELM-270M on the AMD Ryzen AI Max+ 395
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1727k | 298.7-365 t/s | ~11.7-14.3 (slow) |
| Q8 | yes | 1731k | 597.3-730.1 t/s | ~23.3-28.5 (slow) |
| Q4 | yes | 1733k | 1066.7-1303.7 t/s | ~41.7-50.9 (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 OpenELM-270M?▶
Yes. At Q4 it generates ~1066.7-1303.7 tok/s and fits up to 1733k context; beyond that it spills to SSD swap and slows to ~41.7-50.9 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.