NVIDIA A100 40GB PCIe~121 tok/s (Q4)

openai/gpt-oss-20b speed on NVIDIA A100 40GB PCIe

Quantization-specific throughput and VRAM requirements for openai/gpt-oss-20b running on NVIDIA A100 40GB PCIe.

Speed Snapshot

Topline estimate from compatibility data

Modelopenai/gpt-oss-20b

GPUNVIDIA A100 40GB PCIe

Q4 speed121 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	40GB	121 tok/s	✅ Fits
Q8	20GB	40GB	95 tok/s	✅ Fits
FP16	41GB	40GB	51 tok/s	❌ Not recommended