🔌
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 iGPT-L?
Yes — here's how fast and up to what context, with real measured numbers.
iGPT-L on the AMD Ryzen AI Max+ 395
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1693k | 59.2-72.4 t/s | ~2.3-2.8 (slow) |
| Q8 | yes | 1714k | 118.4-144.7 t/s | ~4.6-5.7 (slow) |
| Q4 | yes | 1723k | 211.5-258.4 t/s | ~8.3-10.1 (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 iGPT-L?▶
Yes. At Q4 it generates ~211.5-258.4 tok/s and fits up to 1723k context; beyond that it spills to SSD swap and slows to ~8.3-10.1 tok/s.
How much context fits?▶
At Q4, up to about 1723k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.