// RUN — FITS

Can the Apple M3 Max 36GB run OpenELM-1.1B?

Yes — here's how fast and up to what context, with real measured numbers.

OpenELM-1.1B on the Apple M3 Max 36GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 439k 94.4-113.9 t/s ~3.1-3.8 (slow)
Q8 yes 455k 188.9-227.8 t/s ~6.3-7.6 (slow)
Q4 yes 462k 337.3-406.7 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.

→ All models on the Apple M3 Max 36GB → OpenELM-1.1B specs → Other hardware

FAQ

Can the Apple M3 Max 36GB run OpenELM-1.1B?▶

Yes. At Q4 it generates ~337.3-406.7 tok/s and fits up to 462k 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 462k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.