Apple M4 Pro~18 tok/s (Q4)

openai/gpt-oss-20b speed on Apple M4 Pro

Quantization-specific throughput and VRAM requirements for openai/gpt-oss-20b running on Apple M4 Pro.

Speed Snapshot

Topline estimate from compatibility data

Modelopenai/gpt-oss-20b

GPUApple M4 Pro

Q4 speed18 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	64GB	18 tok/s	✅ Fits
Q8	20GB	64GB	15 tok/s	✅ Fits
FP16	41GB	64GB	8 tok/s	✅ Fits