🔌
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 Japanese-LM-3.6B?
Yes — here's how fast and up to what context, with real measured numbers.
Japanese-LM-3.6B on the AMD Ryzen AI Max+ 395
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1625k | 22.4-27.4 t/s | ~0.9-1.1 (slow) |
| Q8 | yes | 1680k | 44.8-54.8 t/s | ~1.8-2.1 (slow) |
| Q4 | yes | 1704k | 80-97.8 t/s | ~3.1-3.8 (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 Japanese-LM-3.6B?▶
Yes. At Q4 it generates ~80-97.8 tok/s and fits up to 1704k context; beyond that it spills to SSD swap and slows to ~3.1-3.8 tok/s.
How much context fits?▶
At Q4, up to about 1704k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.