🔌
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 M3 Max 64GB run AraELECTRA?
Yes — here's how fast and up to what context, with real measured numbers.
AraELECTRA on the Apple M3 Max 64GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 852k | 1000-1205.9 t/s | ~25-30.1 (slow) |
| Q8 | yes | 854k | 2000-2411.8 t/s | ~50-60.3 (slow) |
| Q4 | yes | 855k | 3571.4-4306.7 t/s | ~89.3-107.7 (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 M3 Max 64GB run AraELECTRA?▶
Yes. At Q4 it generates ~3571.4-4306.7 tok/s and fits up to 855k context; beyond that it spills to SSD swap and slows to ~89.3-107.7 tok/s.
How much context fits?▶
At Q4, up to about 855k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.