can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 5080 (16GB) run Qwen3 14B?

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

Yes — it runs great.

Best fit: Qwen3 14B at Q5_K_M · 10.5 GB · 54–81 tok/s on a NVIDIA RTX 5080 (16GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K5.8 GB85–127 tok/sRuns great
Q3_K_M7.3 GB71–107 tok/sRuns great
Q4_K_M9.0 GB61–92 tok/sRuns great
Q5_K_M10.5 GB54–81 tok/sRuns great
Q6_K12.1 GB48–72 tok/sTight / slow
Q8_015.7 GB39–58 tok/sWon't fit
FP1629.5 GB22–33 tok/sWon't fit

Ran Qwen3 14B on a NVIDIA RTX 5080 (16GB)? Add your real numbers →