Apple M3 Max~11 tok/s (Q4)

AI-MO/Kimina-Prover-72B speed on Apple M3 Max

Quantization-specific throughput and VRAM requirements for AI-MO/Kimina-Prover-72B running on Apple M3 Max.

Speed Snapshot

Topline estimate from compatibility data

ModelAI-MO/Kimina-Prover-72B

GPUApple M3 Max

Q4 speed11 tok/s

Q4 VRAM required35GB

Data Source

Calculation and benchmark status

Speed values come from the compatibility dataset (`estimatedTokensPerSec`) and are sorted by quantization.

For full verdict logic and alternate GPUs, see the canonical compatibility page.

Quantization Speed Table

Quantization	VRAM needed	VRAM available	Speed	Verdict
Q4	35GB	128GB	11 tok/s	✅ Fits
Q8	70GB	128GB	7 tok/s	✅ Fits
FP16	141GB	128GB	4 tok/s	❌ Not recommended