🔌
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 phi-3.5-mini?
Yes — here's how fast and up to what context, with real measured numbers.
phi-3.5-mini on the AMD Ryzen AI Max+ 395
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1619k | 21.2-25.9 t/s | ~0.8-1 (slow) |
| Q8 | yes | 1677k | 42.4-51.9 t/s | ~1.7-2 (slow) |
| Q4 | yes | 1702k | 75.8-92.6 t/s | ~3-3.6 (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 phi-3.5-mini?▶
Yes. At Q4 it generates ~75.8-92.6 tok/s and fits up to 1702k context; beyond that it spills to SSD swap and slows to ~3-3.6 tok/s.
How much context fits?▶
At Q4, up to about 1702k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.