Apple M3 Max~32 tok/s (Q4)

mlx-community/gpt-oss-20b-MXFP4-Q8 speed on Apple M3 Max

Quantization-specific throughput and VRAM requirements for mlx-community/gpt-oss-20b-MXFP4-Q8 running on Apple M3 Max.

Speed Snapshot

Topline estimate from compatibility data

Modelmlx-community/gpt-oss-20b-MXFP4-Q8

GPUApple M3 Max

Q4 speed32 tok/s

Q4 VRAM required10GB

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	10GB	128GB	32 tok/s	✅ Fits
Q8	20GB	128GB	22 tok/s	✅ Fits
FP16	41GB	128GB	12 tok/s	✅ Fits