🔌
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 M4 Max 64GB run MiniCPM-1.2B?
Yes — here's how fast and up to what context, with real measured numbers.
MiniCPM-1.2B on the Apple M4 Max 64GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 818k | 148.8-179.5 t/s | ~2.7-3.3 (slow) |
| Q8 | yes | 837k | 297.6-358.9 t/s | ~5.5-6.6 (slow) |
| Q4 | yes | 845k | 531.5-640.9 t/s | ~9.7-11.7 (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 M4 Max 64GB run MiniCPM-1.2B?▶
Yes. At Q4 it generates ~531.5-640.9 tok/s and fits up to 845k context; beyond that it spills to SSD swap and slows to ~9.7-11.7 tok/s.
How much context fits?▶
At Q4, up to about 845k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.