Rig report
NVIDIA L40S (48GB)
48.0 GB memory · 864 GB/s · 37 of 48 tracked models fit
Best model it can run
Gemma 4 31BRuns great
Q8_0 · 32.6 GB · 18–27 tok/s · capability 84/100
Fastest that fits: Qwen3 Coder Next 80B-A3B (MoE) at 197–295 tok/s
Also runs
Have a NVIDIA L40S (48GB)? Add your real benchmark → to sharpen these numbers for everyone.
Estimates from device specs and model architectures, refined by community benchmarks. See the methodology.