🔌
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 AraBERT LArge v2?
Yes — here's how fast and up to what context, with real measured numbers.
AraBERT LArge v2 on the Apple M2 Ultra 192GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 2603k | 733.2-884.1 t/s | ~9.2-11.1 (slow) |
| Q8 | yes | 2608k | 1466.3-1768.2 t/s | ~18.3-22.1 (slow) |
| Q4 | yes | 2611k | 2618.4-3157.5 t/s | ~32.7-39.5 (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 AraBERT LArge v2?▶
Yes. At Q4 it generates ~2618.4-3157.5 tok/s and fits up to 2611k context; beyond that it spills to SSD swap and slows to ~32.7-39.5 tok/s.
How much context fits?▶
At Q4, up to about 2611k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.