🔌
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 Max 32GB run BGE-M3 Embedding?
Yes — here's how fast and up to what context, with real measured numbers.
BGE-M3 Embedding on the Apple M2 Max 32GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 406k | 406-489.6 t/s | ~10.1-12.2 (slow) |
| Q8 | yes | 411k | 811.9-979.1 t/s | ~20.3-24.5 (slow) |
| Q4 | yes | 414k | 1449.9-1748.4 t/s | ~36.2-43.7 (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 M2 Max 32GB run BGE-M3 Embedding?▶
Yes. At Q4 it generates ~1449.9-1748.4 tok/s and fits up to 414k context; beyond that it spills to SSD swap and slows to ~36.2-43.7 tok/s.
How much context fits?▶
At Q4, up to about 414k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.