Apple M4 Max~80 tok/s (Q4)

black-forest-labs/FLUX.2-dev speed on Apple M4 Max

Quantization-specific throughput and VRAM requirements for black-forest-labs/FLUX.2-dev running on Apple M4 Max.

Speed Snapshot

Topline estimate from compatibility data

Modelblack-forest-labs/FLUX.2-dev

GPUApple M4 Max

Q4 speed80 tok/s

Q4 VRAM required4GB

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	4GB	128GB	80 tok/s	✅ Fits
Q8	8GB	128GB	50 tok/s	✅ Fits
FP16	16GB	128GB	27 tok/s	✅ Fits