🔌
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 Surya?
Yes — here's how fast and up to what context, with real measured numbers.
Surya on the AMD Ryzen AI Max+ 395
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1724k | 220.3-269.3 t/s | ~8.6-10.5 (slow) |
| Q8 | yes | 1729k | 440.7-538.6 t/s | ~17.2-21 (slow) |
| Q4 | yes | 1732k | 786.9-961.7 t/s | ~30.7-37.6 (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 Surya?▶
Yes. At Q4 it generates ~786.9-961.7 tok/s and fits up to 1732k context; beyond that it spills to SSD swap and slows to ~30.7-37.6 tok/s.
How much context fits?▶
At Q4, up to about 1732k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.