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

Can I run Gemma 3n 4B on Apple M2 Ultra (76-core GPU)?

Yes — it runs.best quant:
Decode speed
118 tok/sest
Usable context
33K
Memory
192 GB
Fits in memory118 tok/sest · 33K ctx
Fits in memory101 tok/sest · 33K ctx
Fits in memory68 tok/sest · 33K ctx
What is quantisation? →
Gemma 3n 4B
7.8B · full specs & benchmarks →
Apple M2 Ultra (76-core GPU)
192 GB · everything it runs →