🔌
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 M1 Ultra 64GB run DiT-XL/2?
Yes — here's how fast and up to what context, with real measured numbers.
DiT-XL/2 on the Apple M1 Ultra 64GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 835k | 403-485.9 t/s | ~5-6.1 (slow) |
| Q8 | yes | 846k | 805.9-971.9 t/s | ~10.1-12.1 (slow) |
| Q4 | yes | 850k | 1439.2-1735.4 t/s | ~18-21.7 (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 M1 Ultra 64GB run DiT-XL/2?▶
Yes. At Q4 it generates ~1439.2-1735.4 tok/s and fits up to 850k context; beyond that it spills to SSD swap and slows to ~18-21.7 tok/s.
How much context fits?▶
At Q4, up to about 850k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.