Compatibility check
Can I run Qwen2.5 7B Instruct on GeForce RTX 3060 12GB?
Yes — it runs.best quant:
Decode speed
63 tok/sest
Usable context
33K
Memory
12 GB
Fits in memory63 tok/sest · 33K ctx
Fits in memory53 tok/sest · 33K ctx
Fits in memory36 tok/sest · 16K ctx