🔌
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 ProGen2-xlarge?
Yes — here's how fast and up to what context, with real measured numbers.
ProGen2-xlarge on the Apple M3 Max 48GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 220k | 21.3-25.6 t/s | ~0.5-0.6 (slow) |
| Q8 | yes | 269k | 42.5-51.3 t/s | ~1.1-1.3 (slow) |
| Q4 | yes | 291k | 75.9-91.5 t/s | ~1.9-2.3 (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 ProGen2-xlarge?▶
Yes. At Q4 it generates ~75.9-91.5 tok/s and fits up to 291k context; beyond that it spills to SSD swap and slows to ~1.9-2.3 tok/s.
How much context fits?▶
At Q4, up to about 291k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.