🔌
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 M2 Max 64GB run Unified-IO (XL)?
Yes — here's how fast and up to what context, with real measured numbers.
Unified-IO (XL) on the Apple M2 Max 64GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 767k | 46.5-56.1 t/s | ~1.2-1.4 (slow) |
| Q8 | yes | 811k | 93-112.1 t/s | ~2.3-2.8 (slow) |
| Q4 | yes | 831k | 166.1-200.2 t/s | ~4.2-5 (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 M2 Max 64GB run Unified-IO (XL)?▶
Yes. At Q4 it generates ~166.1-200.2 tok/s and fits up to 831k context; beyond that it spills to SSD swap and slows to ~4.2-5 tok/s.
How much context fits?▶
At Q4, up to about 831k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.