🔌
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 TurboVLA?
Yes — here's how fast and up to what context, with real measured numbers.
TurboVLA on the AMD Ryzen AI Max+ 395
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1729k | 403.2-492.8 t/s | ~15.8-19.3 (slow) |
| Q8 | yes | 1732k | 806.4-985.6 t/s | ~31.5-38.5 (slow) |
| Q4 | yes | 1733k | 1440-1760 t/s | ~56.3-68.8 (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 TurboVLA?▶
Yes. At Q4 it generates ~1440-1760 tok/s and fits up to 1733k context; beyond that it spills to SSD swap and slows to ~56.3-68.8 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.