🔌
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 Baichuan-Omni-1.5?
Yes — here's how fast and up to what context, with real measured numbers.
Baichuan-Omni-1.5 on the AMD Ryzen AI Max+ 395
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 560k | 7.3-9 t/s | ~0.3-0.4 (slow) |
| Q8 | yes | 627k | 14.7-17.9 t/s | ~0.6-0.7 (slow) |
| Q4 | yes | 656k | 26.2-32 t/s | ~1-1.3 (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 Baichuan-Omni-1.5?▶
Yes. At Q4 it generates ~26.2-32 tok/s and fits up to 656k context; beyond that it spills to SSD swap and slows to ~1-1.3 tok/s.
How much context fits?▶
At Q4, up to about 656k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.