Can I Run Qwen 3 on NVIDIA L40S?

Written by Jakub Rusinowski · Last updated July 10, 2026

Yes — the Qwen 3 family runs on the NVIDIA L40S.

Affiliate disclosure: Some links on this page are affiliate links — if you buy through them, LLM Configurator may earn a commission at no extra cost to you. As an Amazon Associate, LLM Configurator earns from qualifying purchases.

Check price on Amazon — NVIDIA L40S 48GB

NVIDIA L40S Specs

VRAM48 GB
Memory Bandwidth864 GB/s

Qwen 3 Variants That Fit

Qwen 3 32BQ4_K_M · 19.5 GB · ~44 tok/s (est.)
Qwen 3 14BQ4_K_M · 9.5 GB · ~91 tok/s (est.)
Qwen 3 30B-A3B (MoE)Q4_K_M · 8 GB · ~400 tok/s (est.)
Qwen 3 8BQ4_K_M · 5.5 GB · ~157 tok/s (est.)

FAQ

Can I run Qwen 3 on the NVIDIA L40S?

Yes — the Qwen 3 family runs on the NVIDIA L40S.

Which Qwen 3 variant fits best on the NVIDIA L40S?

Qwen 3 32B at Q4_K_M quantization (19.5 GB), estimated ~44 tokens/sec.

Qwen 3 on Other GPUs

Popular Models on the NVIDIA L40S

VRAM Tier

Troubleshooting

Buying Guide

← Can I Run It? | Qwen 3 Model Page | NVIDIA L40S GPU Page | Check Your Hardware