LLMap
Models /Gemma 3n 4B /Can I run it?
Compatibility check

Can I run Gemma 3n 4B on GeForce RTX 3090?

Yes — it runs.best quant:
Decode speed
158 tok/sest
Usable context
33K
Memory
24 GB
Fits in memory158 tok/sest · 33K ctx
Fits in memory135 tok/sest · 33K ctx
Fits in memory90 tok/sest · 33K ctx
What is quantisation? →
Gemma 3n 4B
7.8B · full specs & benchmarks →
GeForce RTX 3090
24 GB · everything it runs →