NVIDIA L40~200 tok/s (Q4)

TinyLlama/TinyLlama-1.1B-Chat-v1.0 speed on NVIDIA L40

Quantization-specific throughput and VRAM requirements for TinyLlama/TinyLlama-1.1B-Chat-v1.0 running on NVIDIA L40.

Speed Snapshot

Topline estimate from compatibility data

ModelTinyLlama/TinyLlama-1.1B-Chat-v1.0

GPUNVIDIA L40

Q4 speed200 tok/s

Q4 VRAM required1GB

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	1GB	48GB	200 tok/s	✅ Fits
Q8	1GB	48GB	145 tok/s	✅ Fits
FP16	2GB	48GB	79 tok/s	✅ Fits