// RUN ON APPLE

Run CausalLM 34B β on Apple hardware

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

HardwareEst tok/sFits 8k?Max ctx~Price
Apple M2 Ultra 192GB → ~34.1 yes 580k ~$6,600
Apple M2 Ultra 64GB → ~34.1 yes 141k ~$4,000
Apple M1 Ultra 128GB → ~34.1 yes 360k ~$4,800
Apple M1 Ultra 64GB → ~34.1 yes 141k ~$3,700
Apple M4 Max 64GB → ~23.2 yes 141k ~$3,900
Apple M4 Max 36GB → ~23.2 yes 44k ~$3,000
Apple M4 Max 128GB → ~23.2 yes 360k ~$4,900
Apple M4 Max 48GB → ~23.2 yes 86k ~$3,300
Apple M1 Max 32GB → ~17 yes 31k ~$2,000
Apple M3 Max 48GB → ~17 yes 86k ~$3,200
Apple M3 Max 64GB → ~17 yes 141k ~$3,700
Apple M3 Max 128GB → ~17 yes 360k ~$4,700
Apple M1 Max 64GB → ~17 yes 141k ~$2,600
Apple M2 Max 32GB → ~17 yes 31k ~$2,200
Apple M2 Max 64GB → ~17 yes 141k ~$2,800
Apple M2 Max 96GB → ~17 yes 250k ~$3,300
Apple M3 Max 36GB → ~12.8 yes 44k ~$2,900

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

FAQ

What Apple hardware runs CausalLM 34B β?

On GenAIList, 17 Apple options can run CausalLM 34B β at Q4 — the fastest is the Apple M2 Ultra 192GB at ~34.1 tok/s.

How fast is CausalLM 34B β on Apple hardware?

Estimated generation speed ranges from ~12.8 to ~34.1 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.