🔌
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 DiffDock?
Yes — here's how fast and up to what context, with real measured numbers.
DiffDock on the AMD Ryzen AI Max+ 395
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1734k | 3984.2-4869.6 t/s | ~155.6-190.2 (slow) |
| Q8 | yes | 1735k | 7968.4-9739.1 t/s | ~311.3-380.4 (slow) |
| Q4 | yes | 1735k | 14229.2-17391.3 t/s | ~555.8-679.3 (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 DiffDock?▶
Yes. At Q4 it generates ~14229.2-17391.3 tok/s and fits up to 1735k context; beyond that it spills to SSD swap and slows to ~555.8-679.3 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.