🔌
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 96GB run OpenELM-3B?
Yes — here's how fast and up to what context, with real measured numbers.
OpenELM-3B on the Apple M2 Max 96GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1203k | 44.7-53.9 t/s | ~1.1-1.3 (slow) |
| Q8 | yes | 1249k | 89.5-107.9 t/s | ~2.2-2.7 (slow) |
| Q4 | yes | 1269k | 159.8-192.7 t/s | ~4-4.8 (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 96GB run OpenELM-3B?▶
Yes. At Q4 it generates ~159.8-192.7 tok/s and fits up to 1269k context; beyond that it spills to SSD swap and slows to ~4-4.8 tok/s.
How much context fits?▶
At Q4, up to about 1269k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.