// RUN โ€” FITS

Can the Apple M2 Ultra 192GB run Nucleotide Transformer?

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

Nucleotide Transformer on the Apple M2 Ultra 192GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 2538k 108.8-131.2 t/s ~1.4-1.6 (slow)
Q8 yes 2576k 217.6-262.4 t/s ~2.7-3.3 (slow)
Q4 yes 2592k 388.6-468.6 t/s ~4.9-5.9 (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 M2 Ultra 192GB run Nucleotide Transformer?โ–ถ

Yes. At Q4 it generates ~388.6-468.6 tok/s and fits up to 2592k context; beyond that it spills to SSD swap and slows to ~4.9-5.9 tok/s.

How much context fits?โ–ถ

At Q4, up to about 2592k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.