🔌
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 AWD-LSTM-MoS + dynamic evaluation (PTB, 2018)?
Yes — here's how fast and up to what context, with real measured numbers.
AWD-LSTM-MoS + dynamic evaluation (PTB, 2018) on the AMD Ryzen AI Max+ 395
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1734k | 3360-4106.7 t/s | ~131.3-160.4 (slow) |
| Q8 | yes | 1735k | 6720-8213.3 t/s | ~262.5-320.8 (slow) |
| Q4 | yes | 1735k | 12000-14666.7 t/s | ~468.8-572.9 (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
→ AWD-LSTM-MoS + dynamic evaluation (PTB, 2018) specs
→ Other hardware
FAQ
Can the AMD Ryzen AI Max+ 395 run AWD-LSTM-MoS + dynamic evaluation (PTB, 2018)?▶
Yes. At Q4 it generates ~12000-14666.7 tok/s and fits up to 1735k context; beyond that it spills to SSD swap and slows to ~468.8-572.9 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.