🔌
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 128GB run Playground v2.5?
Yes — here's how fast and up to what context, with real measured numbers.
Playground v2.5 on the Apple M1 Ultra 128GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1628k | 77.7-93.7 t/s | ~1-1.2 (slow) |
| Q8 | yes | 1682k | 155.4-187.4 t/s | ~1.9-2.3 (slow) |
| Q4 | yes | 1705k | 277.6-334.7 t/s | ~3.5-4.2 (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 128GB run Playground v2.5?▶
Yes. At Q4 it generates ~277.6-334.7 tok/s and fits up to 1705k context; beyond that it spills to SSD swap and slows to ~3.5-4.2 tok/s.
How much context fits?▶
At Q4, up to about 1705k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.