🔌
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 Ultra 192GB run ALBERT?
Yes — here's how fast and up to what context, with real measured numbers.
ALBERT on the Apple M2 Ultra 192GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 2613k | 15111.1-18222.2 t/s | ~188.9-227.8 (slow) |
| Q8 | yes | 2614k | 30222.2-36444.4 t/s | ~377.8-455.6 (slow) |
| Q4 | yes | 2614k | 53968.3-65079.4 t/s | ~674.6-813.5 (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 Ultra 192GB run ALBERT?▶
Yes. At Q4 it generates ~53968.3-65079.4 tok/s and fits up to 2614k context; beyond that it spills to SSD swap and slows to ~674.6-813.5 tok/s.
How much context fits?▶
At Q4, up to about 2614k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.