NVIDIA L40~36 tok/s (Q4)

Qwen/Qwen2.5-72B-Instruct speed on NVIDIA L40

Quantization-specific throughput and VRAM requirements for Qwen/Qwen2.5-72B-Instruct running on NVIDIA L40.

Speed Snapshot

Topline estimate from compatibility data

ModelQwen/Qwen2.5-72B-Instruct

GPUNVIDIA L40

Q4 speed36 tok/s

Q4 VRAM required35GB

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	35GB	48GB	36 tok/s	✅ Fits
Q8	70GB	48GB	21 tok/s	❌ Not recommended
FP16	141GB	48GB	12 tok/s	❌ Not recommended