🔌
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 EmbeddingGemma?
Yes — here's how fast and up to what context, with real measured numbers.
EmbeddingGemma on the AMD Ryzen AI Max+ 395
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1726k | 261.8-320 t/s | ~10.2-12.5 (slow) |
| Q8 | yes | 1730k | 523.6-640 t/s | ~20.5-25 (slow) |
| Q4 | yes | 1732k | 935.1-1142.9 t/s | ~36.5-44.6 (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 EmbeddingGemma?▶
Yes. At Q4 it generates ~935.1-1142.9 tok/s and fits up to 1732k context; beyond that it spills to SSD swap and slows to ~36.5-44.6 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.