Compatibility check
Can I run Qwen2.5 7B Instruct on GeForce RTX 4070 SUPER?
Yes — it runs.best quant:
Decode speed
88 tok/sest
Usable context
33K
Memory
12 GB
Fits in memory88 tok/sest · 33K ctx
Fits in memory75 tok/sest · 33K ctx
Fits in memory50 tok/sest · 16K ctx