// RUN ON APPLE

Run BGE-M3 Embedding on Apple hardware

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

HardwareEst tok/sFits 8k?Max ctx~Price
Apple M2 Ultra 192GB โ†’ ~3,496.8 yes 2611k ~$6,600
Apple M2 Ultra 64GB โ†’ ~3,496.8 yes 853k ~$4,000
Apple M1 Ultra 128GB โ†’ ~3,496.8 yes 1732k ~$4,800
Apple M1 Ultra 64GB โ†’ ~3,496.8 yes 853k ~$3,700
Apple M4 Max 64GB โ†’ ~2,386.6 yes 853k ~$3,900
Apple M4 Max 36GB โ†’ ~2,386.6 yes 469k ~$3,000
Apple M4 Max 128GB โ†’ ~2,386.6 yes 1732k ~$4,900
Apple M4 Max 48GB โ†’ ~2,386.6 yes 633k ~$3,300
Apple M1 Max 32GB โ†’ ~1,748.4 yes 414k ~$2,000
Apple M3 Max 48GB โ†’ ~1,748.4 yes 633k ~$3,200
Apple M3 Max 64GB โ†’ ~1,748.4 yes 853k ~$3,700
Apple M3 Max 128GB โ†’ ~1,748.4 yes 1732k ~$4,700
Apple M1 Max 64GB โ†’ ~1,748.4 yes 853k ~$2,600
Apple M2 Max 32GB โ†’ ~1,748.4 yes 414k ~$2,200
Apple M2 Max 64GB โ†’ ~1,748.4 yes 853k ~$2,800
Apple M2 Max 96GB โ†’ ~1,748.4 yes 1293k ~$3,300
Apple M3 Max 36GB โ†’ ~1,311.3 yes 469k ~$2,900
NVIDIA GeForce RTX 2050 โ†’ ~519.4 yes 73k โ€”

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

FAQ

What Apple hardware runs BGE-M3 Embedding?โ–ถ

On GenAIList, 18 Apple options can run BGE-M3 Embedding at Q4 โ€” the fastest is the Apple M2 Ultra 192GB at ~3,496.8 tok/s.

How fast is BGE-M3 Embedding on Apple hardware?โ–ถ

Estimated generation speed ranges from ~519.4 to ~3,496.8 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.