🔌
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 AbLang (heavy sequences)?
Yes — here's how fast and up to what context, with real measured numbers.
AbLang (heavy sequences) on the AMD Ryzen AI Max+ 395
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1724k | 227.2-277.6 t/s | ~8.9-10.8 (slow) |
| Q8 | yes | 1730k | 454.3-555.3 t/s | ~17.7-21.7 (slow) |
| Q4 | yes | 1732k | 811.3-991.5 t/s | ~31.7-38.7 (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 AbLang (heavy sequences)?▶
Yes. At Q4 it generates ~811.3-991.5 tok/s and fits up to 1732k context; beyond that it spills to SSD swap and slows to ~31.7-38.7 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.