AMD Instinct MI300X~413 tok/s (Q4)

openai/gpt-oss-20b speed on AMD Instinct MI300X

Quantization-specific throughput and VRAM requirements for openai/gpt-oss-20b running on AMD Instinct MI300X.

Speed Snapshot

Topline estimate from compatibility data

Modelopenai/gpt-oss-20b

GPUAMD Instinct MI300X

Q4 speed413 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	192GB	413 tok/s	✅ Fits
Q8	20GB	192GB	293 tok/s	✅ Fits
FP16	41GB	192GB	154 tok/s	✅ Fits