NVIDIA L40~63 tok/s (Q4)

moonshotai/Kimi-Linear-48B-A3B-Instruct speed on NVIDIA L40

Quantization-specific throughput and VRAM requirements for moonshotai/Kimi-Linear-48B-A3B-Instruct running on NVIDIA L40.

Speed Snapshot

Topline estimate from compatibility data

Modelmoonshotai/Kimi-Linear-48B-A3B-Instruct

GPUNVIDIA L40

Q4 speed63 tok/s

Q4 VRAM required25GB

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	25GB	48GB	63 tok/s	✅ Fits
Q8	50GB	48GB	44 tok/s	❌ Not recommended
FP16	101GB	48GB	21 tok/s	❌ Not recommended