🔌
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 UniRep?
Yes — here's how fast and up to what context, with real measured numbers.
UniRep on the Apple M1 Ultra 64GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 855k | 14945.1-18022 t/s | ~186.8-225.3 (slow) |
| Q8 | yes | 856k | 29890.1-36044 t/s | ~373.6-450.5 (slow) |
| Q4 | yes | 856k | 53375.2-64364.2 t/s | ~667.2-804.6 (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 UniRep?▶
Yes. At Q4 it generates ~53375.2-64364.2 tok/s and fits up to 856k context; beyond that it spills to SSD swap and slows to ~667.2-804.6 tok/s.
How much context fits?▶
At Q4, up to about 856k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.