AMD Instinct MI250X~283 tok/s (Q4)

openai/gpt-oss-safeguard-20b speed on AMD Instinct MI250X

Quantization-specific throughput and VRAM requirements for openai/gpt-oss-safeguard-20b running on AMD Instinct MI250X.

Speed Snapshot

Topline estimate from compatibility data

Modelopenai/gpt-oss-safeguard-20b

GPUAMD Instinct MI250X

Q4 speed283 tok/s

Q4 VRAM required11GB

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	11GB	128GB	283 tok/s	✅ Fits
Q8	22GB	128GB	192 tok/s	✅ Fits
FP16	44GB	128GB	90 tok/s	✅ Fits