can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 4080 (16GB) run Qwen3.8 27B?

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

Yes, but it's tight.

Best fit: Qwen3.8 27B at Q3_K_M · 11.8 GB · 37–55 tok/s on a NVIDIA RTX 4080 (16GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M11.8 GB37–55 tok/sTight / slow
Q4_K_M16.6 GB28–42 tok/sWon't fit
Q5_K_M19.5 GB24–36 tok/sWon't fit
Q6_K22.5 GB21–32 tok/sWon't fit
Q8_029.0 GB17–25 tok/sWon't fit
FP1654.6 GB9–14 tok/sWon't fit

Ran Qwen3.8 27B on a NVIDIA RTX 4080 (16GB)? Add your real numbers →