// RUN — FITS

Can the Apple M2 Max 96GB run OpenELM-1.1B?

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

OpenELM-1.1B on the Apple M2 Max 96GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 1263k 125.9-151.9 t/s ~3.1-3.8 (slow)
Q8 yes 1279k 251.9-303.7 t/s ~6.3-7.6 (slow)
Q4 yes 1286k 449.7-542.3 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.

→ All models on the Apple M2 Max 96GB → OpenELM-1.1B specs → Other hardware

FAQ

Can the Apple M2 Max 96GB run OpenELM-1.1B?▶

Yes. At Q4 it generates ~449.7-542.3 tok/s and fits up to 1286k 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 1286k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.