🔌
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 BiomedGPT (182M)?
Yes — here's how fast and up to what context, with real measured numbers.
BiomedGPT (182M) on the AMD Ryzen AI Max+ 395
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1729k | 443.1-541.5 t/s | ~17.3-21.2 (slow) |
| Q8 | yes | 1732k | 886.2-1083.1 t/s | ~34.6-42.3 (slow) |
| Q4 | yes | 1733k | 1582.4-1934.1 t/s | ~61.8-75.5 (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 BiomedGPT (182M)?▶
Yes. At Q4 it generates ~1582.4-1934.1 tok/s and fits up to 1733k context; beyond that it spills to SSD swap and slows to ~61.8-75.5 tok/s.
How much context fits?▶
At Q4, up to about 1733k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.