// RUN ON APPLE

Run Qwen-VL on Apple hardware

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

HardwareEst tok/sFits 8k?Max ctx~Price
Apple M2 Ultra 192GB โ†’ ~122 yes 1266k ~$6,600
Apple M2 Ultra 64GB โ†’ ~122 yes 387k ~$4,000
Apple M1 Ultra 128GB โ†’ ~122 yes 826k ~$4,800
Apple M1 Ultra 64GB โ†’ ~122 yes 387k ~$3,700
Apple M4 Max 64GB โ†’ ~83.3 yes 387k ~$3,900
Apple M4 Max 36GB โ†’ ~83.3 yes 195k ~$3,000
Apple M4 Max 128GB โ†’ ~83.3 yes 826k ~$4,900
Apple M4 Max 48GB โ†’ ~83.3 yes 277k ~$3,300
Apple M1 Max 32GB โ†’ ~61 yes 167k ~$2,000
Apple M3 Max 48GB โ†’ ~61 yes 277k ~$3,200
Apple M3 Max 64GB โ†’ ~61 yes 387k ~$3,700
Apple M3 Max 128GB โ†’ ~61 yes 826k ~$4,700
Apple M1 Max 64GB โ†’ ~61 yes 387k ~$2,600
Apple M2 Max 32GB โ†’ ~61 yes 167k ~$2,200
Apple M2 Max 64GB โ†’ ~61 yes 387k ~$2,800
Apple M2 Max 96GB โ†’ ~61 yes 607k ~$3,300
Apple M3 Max 36GB โ†’ ~45.8 yes 195k ~$2,900

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

FAQ

What Apple hardware runs Qwen-VL?โ–ถ

On GenAIList, 17 Apple options can run Qwen-VL at Q4 โ€” the fastest is the Apple M2 Ultra 192GB at ~122 tok/s.

How fast is Qwen-VL on Apple hardware?โ–ถ

Estimated generation speed ranges from ~45.8 to ~122 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.