🔌
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 48GB run Infinity?
Yes — here's how fast and up to what context, with real measured numbers.
Infinity on the Apple M4 Max 48GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 575k | 92.8-111.9 t/s | ~1.7-2.1 (slow) |
| Q8 | yes | 606k | 185.6-223.9 t/s | ~3.4-4.1 (slow) |
| Q4 | yes | 619k | 331.5-399.8 t/s | ~6.1-7.3 (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 M4 Max 48GB run Infinity?▶
Yes. At Q4 it generates ~331.5-399.8 tok/s and fits up to 619k context; beyond that it spills to SSD swap and slows to ~6.1-7.3 tok/s.
How much context fits?▶
At Q4, up to about 619k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.