can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA L40S (48GB) run Qwen3 8B?

Qwen · Apache 2.0 · estimated for a 48.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Qwen3 8B at FP16 · 16.4 GB · 34–51 tok/s on a NVIDIA L40S (48GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K3.3 GB113–170 tok/sRuns great
Q3_K_M4.1 GB99–148 tok/sRuns great
Q4_K_M5.0 GB87–130 tok/sRuns great
Q5_K_M5.9 GB78–117 tok/sRuns great
Q6_K6.7 GB70–105 tok/sRuns great
Q8_08.7 GB58–87 tok/sRuns great
FP1616.4 GB34–51 tok/sRuns great

Ran Qwen3 8B on a NVIDIA L40S (48GB)? Add your real numbers →