🔌
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 M3 Max 36GB run Pythia-160m?
Yes — here's how fast and up to what context, with real measured numbers.
Pythia-160m on the Apple M3 Max 36GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 467k | 637.5-768.8 t/s | ~21.3-25.6 (slow) |
| Q8 | yes | 469k | 1275-1537.5 t/s | ~42.5-51.3 (slow) |
| Q4 | yes | 470k | 2276.8-2745.5 t/s | ~75.9-91.5 (slow) |
Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.
FAQ
Can the Apple M3 Max 36GB run Pythia-160m?▶
Yes. At Q4 it generates ~2276.8-2745.5 tok/s and fits up to 470k context; beyond that it spills to SSD swap and slows to ~75.9-91.5 tok/s.
How much context fits?▶
At Q4, up to about 470k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.