🔌
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 Selfish-RNN (SNT-ASGD) Stacked LSTMs?
Yes — here's how fast and up to what context, with real measured numbers.
Selfish-RNN (SNT-ASGD) Stacked LSTMs on the AMD Ryzen AI Max+ 395
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1734k | 3200-3911.1 t/s | ~125-152.8 (slow) |
| Q8 | yes | 1735k | 6400-7822.2 t/s | ~250-305.6 (slow) |
| Q4 | yes | 1735k | 11428.6-13968.3 t/s | ~446.4-545.6 (slow) |
Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.
→ All models on the AMD Ryzen AI Max+ 395
→ Selfish-RNN (SNT-ASGD) Stacked LSTMs specs
→ Other hardware
FAQ
Can the AMD Ryzen AI Max+ 395 run Selfish-RNN (SNT-ASGD) Stacked LSTMs?▶
Yes. At Q4 it generates ~11428.6-13968.3 tok/s and fits up to 1735k context; beyond that it spills to SSD swap and slows to ~446.4-545.6 tok/s.
How much context fits?▶
At Q4, up to about 1735k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.