🔌
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 Stable LM 2 12B?
Yes — here's how fast and up to what context, with real measured numbers.
Stable LM 2 12B on the AMD Ryzen AI Max+ 395
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 546k | 6.6-8.1 t/s | ~0.3-0.3 (slow) |
| Q8 | yes | 620k | 13.3-16.2 t/s | ~0.5-0.6 (slow) |
| Q4 | yes | 652k | 23.7-29 t/s | ~0.9-1.1 (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 Stable LM 2 12B?▶
Yes. At Q4 it generates ~23.7-29 tok/s and fits up to 652k context; beyond that it spills to SSD swap and slows to ~0.9-1.1 tok/s.
How much context fits?▶
At Q4, up to about 652k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.