🔌
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 Apple M2 Max 32GB run Pythia-410m?
Yes — here's how fast and up to what context, with real measured numbers.
Pythia-410m on the Apple M2 Max 32GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 404k | 331.7-400 t/s | ~8.3-10 (slow) |
| Q8 | yes | 410k | 663.4-800 t/s | ~16.6-20 (slow) |
| Q4 | yes | 413k | 1184.7-1428.6 t/s | ~29.6-35.7 (slow) |
Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.
FAQ
Can the Apple M2 Max 32GB run Pythia-410m?▶
Yes. At Q4 it generates ~1184.7-1428.6 tok/s and fits up to 413k context; beyond that it spills to SSD swap and slows to ~29.6-35.7 tok/s.
How much context fits?▶
At Q4, up to about 413k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.