// RUN — FITS

Can the Apple M2 Ultra 192GB run WizardCoder-15.5B?

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

WizardCoder-15.5B on the Apple M2 Ultra 192GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 535k 17.5-21.2 t/s ~0.2-0.3 (slow)
Q8 yes 594k 35.1-42.3 t/s ~0.4-0.5 (slow)
Q4 yes 620k 62.7-75.6 t/s ~0.8-0.9 (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 Ultra 192GB → WizardCoder-15.5B specs → Other hardware

FAQ

Can the Apple M2 Ultra 192GB run WizardCoder-15.5B?▶

Yes. At Q4 it generates ~62.7-75.6 tok/s and fits up to 620k context; beyond that it spills to SSD swap and slows to ~0.8-0.9 tok/s.

How much context fits?▶

At Q4, up to about 620k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.