Models /Qwen3 30B A3B Thinking 2507 /Can I run it?

Compatibility check

Can I run Qwen3 30B A3B Thinking 2507 on GeForce RTX 5090?

Yes — it runs.best quant:

Decode speed

670 tok/sest

Usable context

66K

Memory

32 GB

Fits in memory670 tok/sest · 66K ctx

Fits in memory571 tok/sest · 33K ctx

Spills to system RAM

What is quantisation? →

Qwen3 30B A3B Thinking 2507

30.5B / 3B · full specs & benchmarks →

GeForce RTX 5090

32 GB · everything it runs →