NVIDIA L40~90 tok/s (Q4)

unsloth/gpt-oss-20b-BF16 speed on NVIDIA L40

Quantization-specific throughput and VRAM requirements for unsloth/gpt-oss-20b-BF16 running on NVIDIA L40.

Speed Snapshot

Topline estimate from compatibility data

Modelunsloth/gpt-oss-20b-BF16

GPUNVIDIA L40

Q4 speed90 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	48GB	90 tok/s	✅ Fits
Q8	20GB	48GB	63 tok/s	✅ Fits
FP16	41GB	48GB	33 tok/s	✅ Fits