can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 4060 Ti (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 · 16–24 tok/s on a NVIDIA RTX 4060 Ti (16GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M11.8 GB16–24 tok/sTight / slow
Q4_K_M16.6 GB12–17 tok/sWon't fit
Q5_K_M19.5 GB10–15 tok/sWon't fit
Q6_K22.5 GB9–13 tok/sWon't fit
Q8_029.0 GB7–10 tok/sWon't fit
FP1654.6 GB4–6 tok/sWon't fit

Ran Qwen3.8 27B on a NVIDIA RTX 4060 Ti (16GB)? Add your real numbers →