🔌
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 Routing Transformer (WT-103)?
Yes — here's how fast and up to what context, with real measured numbers.
Routing Transformer (WT-103) on the AMD Ryzen AI Max+ 395
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1732k | 1014.3-1239.7 t/s | ~39.6-48.4 (slow) |
| Q8 | yes | 1734k | 2028.7-2479.5 t/s | ~79.2-96.9 (slow) |
| Q4 | yes | 1734k | 3622.6-4427.7 t/s | ~141.5-173 (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 Routing Transformer (WT-103)?▶
Yes. At Q4 it generates ~3622.6-4427.7 tok/s and fits up to 1734k context; beyond that it spills to SSD swap and slows to ~141.5-173 tok/s.
How much context fits?▶
At Q4, up to about 1734k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.