can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 4080 (16GB) run Qwen3 8B?

Qwen · Apache 2.0 · estimated for a 16.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Qwen3 8B at Q8_0 · 8.7 GB · 49–74 tok/s on a NVIDIA RTX 4080 (16GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K3.3 GB99–149 tok/sRuns great
Q3_K_M4.1 GB86–129 tok/sRuns great
Q4_K_M5.0 GB75–112 tok/sRuns great
Q5_K_M5.9 GB67–101 tok/sRuns great
Q6_K6.7 GB60–90 tok/sRuns great
Q8_08.7 GB49–74 tok/sRuns great
FP1616.4 GB29–43 tok/sWon't fit

Ran Qwen3 8B on a NVIDIA RTX 4080 (16GB)? Add your real numbers →