Compatibility check
Can I run Qwen2.5 Coder 32B Instruct on GeForce RTX 5090?
Yes — it runs.best quant:
Decode speed
72 tok/sest
Usable context
16K
Memory
32 GB
Fits in memory72 tok/sest · 16K ctx
Fits in memory62 tok/sest · 16K ctx
Spills to system RAM