🔌
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 GPT-NeoX-Japanese?
Yes — here's how fast and up to what context, with real measured numbers.
GPT-NeoX-Japanese on the AMD Ryzen AI Max+ 395
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1653k | 29.9-36.5 t/s | ~1.2-1.4 (slow) |
| Q8 | yes | 1694k | 59.7-73 t/s | ~2.3-2.9 (slow) |
| Q4 | yes | 1712k | 106.7-130.4 t/s | ~4.2-5.1 (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 GPT-NeoX-Japanese?▶
Yes. At Q4 it generates ~106.7-130.4 tok/s and fits up to 1712k context; beyond that it spills to SSD swap and slows to ~4.2-5.1 tok/s.
How much context fits?▶
At Q4, up to about 1712k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.