// RUN — FITS

Can the Apple M2 Ultra 192GB run Pharia-1-LLM-7B?

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

Pharia-1-LLM-7B on the Apple M2 Ultra 192GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 1199k 38.6-46.6 t/s ~0.5-0.6 (slow)
Q8 yes 1253k 77.3-93.2 t/s ~1-1.2 (slow)
Q4 yes 1277k 138-166.4 t/s ~1.7-2.1 (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 → Pharia-1-LLM-7B specs → Other hardware

FAQ

Can the Apple M2 Ultra 192GB run Pharia-1-LLM-7B?▶

Yes. At Q4 it generates ~138-166.4 tok/s and fits up to 1277k context; beyond that it spills to SSD swap and slows to ~1.7-2.1 tok/s.

How much context fits?▶

At Q4, up to about 1277k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.