🔌
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 TinyLlama-1.1B (3T token checkpoint)?
Yes — here's how fast and up to what context, with real measured numbers.
TinyLlama-1.1B (3T token checkpoint) on the AMD Ryzen AI Max+ 395
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1701k | 73.3-89.6 t/s | ~2.9-3.5 (slow) |
| Q8 | yes | 1718k | 146.6-179.2 t/s | ~5.7-7 (slow) |
| Q4 | yes | 1726k | 261.8-320 t/s | ~10.2-12.5 (slow) |
Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.
→ All models on the AMD Ryzen AI Max+ 395
→ TinyLlama-1.1B (3T token checkpoint) specs
→ Other hardware
FAQ
Can the AMD Ryzen AI Max+ 395 run TinyLlama-1.1B (3T token checkpoint)?▶
Yes. At Q4 it generates ~261.8-320 tok/s and fits up to 1726k context; beyond that it spills to SSD swap and slows to ~10.2-12.5 tok/s.
How much context fits?▶
At Q4, up to about 1726k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.