Can I run this LLM?

Can a NVIDIA RTX 5070 Ti (16GB) run Qwen3 Coder 30B-A3B (MoE)?

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

Yes — it runs great.

Best fit: Qwen3 Coder 30B-A3B (MoE) at Q2_K · 11.3 GB · 200–300 tok/s on a NVIDIA RTX 5070 Ti (16GB).

Every quantization on this machine

Quant	Size	Speed	Fit
Q2_K	11.3 GB	200–300 tok/s	Runs great
Q3_K_M	14.7 GB	181–272 tok/s	Won't fit
Q4_K_M	18.6 GB	164–246 tok/s	Won't fit
Q5_K_M	21.7 GB	152–229 tok/s	Won't fit
Q6_K	25.1 GB	142–213 tok/s	Won't fit
Q8_0	32.5 GB	123–184 tok/s	Won't fit
FP16	61.1 GB	81–121 tok/s	Won't fit

Ran Qwen3 Coder 30B-A3B (MoE) on a NVIDIA RTX 5070 Ti (16GB)? Add your real numbers →