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

Can I run Gemma 3n 4B on GeForce RTX 5070?

Yes — it runs.best quant:
Decode speed
114 tok/sest
Usable context
33K
Memory
12 GB
Fits in memory114 tok/sest · 33K ctx
Fits in memory97 tok/sest · 33K ctx
Fits in memoryest65 tok/sest · 16K ctx
What is quantisation? →
Gemma 3n 4B
7.8B · full specs & benchmarks →
GeForce RTX 5070
12 GB · everything it runs →