🔌
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 Retrieval-Augmented Generator?
Yes — here's how fast and up to what context, with real measured numbers.
Retrieval-Augmented Generator on the Apple M1 Ultra 128GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1716k | 434.5-524 t/s | ~5.4-6.5 (slow) |
| Q8 | yes | 1725k | 869-1047.9 t/s | ~10.9-13.1 (slow) |
| Q4 | yes | 1730k | 1551.8-1871.3 t/s | ~19.4-23.4 (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 Retrieval-Augmented Generator?▶
Yes. At Q4 it generates ~1551.8-1871.3 tok/s and fits up to 1730k context; beyond that it spills to SSD swap and slows to ~19.4-23.4 tok/s.
How much context fits?▶
At Q4, up to about 1730k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.