🔌
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 Gemma 3 4B?
Yes — here's how fast and up to what context, with real measured numbers.
Gemma 3 4B on the AMD Ryzen AI Max+ 395
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1613k | 20.2-24.6 t/s | ~0.8-1 (slow) |
| Q8 | yes | 1674k | 40.3-49.3 t/s | ~1.6-1.9 (slow) |
| Q4 | yes | 1701k | 72-88 t/s | ~2.8-3.4 (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 Gemma 3 4B?▶
Yes. At Q4 it generates ~72-88 tok/s and fits up to 1701k context; beyond that it spills to SSD swap and slows to ~2.8-3.4 tok/s.
How much context fits?▶
At Q4, up to about 1701k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.