🔌
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 DeBERTa?
Yes — here's how fast and up to what context, with real measured numbers.
DeBERTa on the AMD Ryzen AI Max+ 395
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1689k | 53.8-65.7 t/s | ~2.1-2.6 (slow) |
| Q8 | yes | 1712k | 107.5-131.4 t/s | ~4.2-5.1 (slow) |
| Q4 | yes | 1722k | 192-234.7 t/s | ~7.5-9.2 (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 DeBERTa?▶
Yes. At Q4 it generates ~192-234.7 tok/s and fits up to 1722k context; beyond that it spills to SSD swap and slows to ~7.5-9.2 tok/s.
How much context fits?▶
At Q4, up to about 1722k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.