🔌
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 48GB run ProtGPT2?
Yes — here's how fast and up to what context, with real measured numbers.
ProtGPT2 on the Apple M3 Max 48GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 614k | 184.3-222.2 t/s | ~4.6-5.6 (slow) |
| Q8 | yes | 625k | 368.6-444.4 t/s | ~9.2-11.1 (slow) |
| Q4 | yes | 630k | 658.1-793.7 t/s | ~16.5-19.8 (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 48GB run ProtGPT2?▶
Yes. At Q4 it generates ~658.1-793.7 tok/s and fits up to 630k context; beyond that it spills to SSD swap and slows to ~16.5-19.8 tok/s.
How much context fits?▶
At Q4, up to about 630k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.