🔌
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 M4 Max 48GB run OpenELM-1.1B?
Yes — here's how fast and up to what context, with real measured numbers.
OpenELM-1.1B on the Apple M4 Max 48GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 603k | 171.9-207.3 t/s | ~3.1-3.8 (slow) |
| Q8 | yes | 620k | 343.8-414.6 t/s | ~6.3-7.6 (slow) |
| Q4 | yes | 627k | 613.9-740.3 t/s | ~11.2-13.6 (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 M4 Max 48GB run OpenELM-1.1B?▶
Yes. At Q4 it generates ~613.9-740.3 tok/s and fits up to 627k context; beyond that it spills to SSD swap and slows to ~11.2-13.6 tok/s.
How much context fits?▶
At Q4, up to about 627k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.