Question 1

Can a NVIDIA RTX 5080 (16GB) run Qwen3.6 27B?

Accepted Answer

Yes — Qwen3.6 27B runs at Q2_K (11.9 GB) at about 50–76 tok/s on a NVIDIA RTX 5080 (16GB).

Question 2

How much memory does Qwen3.6 27B need?

Accepted Answer

Qwen3.6 27B needs about 12.9 GB at 4K context at its smallest quantization. A NVIDIA RTX 5080 (16GB) has 16.0 GB.

Quant	Size	Speed	Fit
Q2_K	11.9 GB	50–76 tok/s	Runs great
Q3_K_M	13.6 GB	45–67 tok/s	Won't fit
Q4_K_M	16.8 GB	37–56 tok/s	Won't fit
Q5_K_M	19.5 GB	33–49 tok/s	Won't fit
Q6_K	22.5 GB	29–43 tok/s	Won't fit
Q8_0	28.6 GB	23–35 tok/s	Won't fit
FP16	53.8 GB	13–19 tok/s	Won't fit