// RUN ON APPLE

Run NLLB on Apple hardware

13 options ranked by estimated speed at Q4 / 8k context.

HardwareEst tok/sFits 8k?Max ctx~Price
Apple M2 Ultra 192GB โ†’ ~21.5 yes 430k ~$6,600
Apple M2 Ultra 64GB โ†’ ~21.5 yes 78k ~$4,000
Apple M1 Ultra 128GB โ†’ ~21.5 yes 254k ~$4,800
Apple M1 Ultra 64GB โ†’ ~21.5 yes 78k ~$3,700
Apple M4 Max 64GB โ†’ ~14.7 yes 78k ~$3,900
Apple M4 Max 128GB โ†’ ~14.7 yes 254k ~$4,900
Apple M4 Max 48GB โ†’ ~14.7 yes 34k ~$3,300
Apple M3 Max 48GB โ†’ ~10.7 yes 34k ~$3,200
Apple M3 Max 64GB โ†’ ~10.7 yes 78k ~$3,700
Apple M3 Max 128GB โ†’ ~10.7 yes 254k ~$4,700
Apple M1 Max 64GB โ†’ ~10.7 yes 78k ~$2,600
Apple M2 Max 64GB โ†’ ~10.7 yes 78k ~$2,800
Apple M2 Max 96GB โ†’ ~10.7 yes 166k ~$3,300

Estimate at Q4 (memory-bound). Click any option for its full per-hardware estimate and measured numbers.

FAQ

What Apple hardware runs NLLB?โ–ถ

On GenAIList, 13 Apple options can run NLLB at Q4 โ€” the fastest is the Apple M2 Ultra 192GB at ~21.5 tok/s.

How fast is NLLB on Apple hardware?โ–ถ

Estimated generation speed ranges from ~10.7 to ~21.5 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.