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

Can I run Gemma 3n 4B on Instinct MI300X?

Yes — it runs.best quant:
Decode speed
729 tok/sest
Usable context
33K
Memory
192 GB
Fits in memory729 tok/sest · 33K ctx
Fits in memory621 tok/sest · 33K ctx
Fits in memory416 tok/sest · 33K ctx
What is quantisation? →
Gemma 3n 4B
7.8B · full specs & benchmarks →
Instinct MI300X
192 GB · everything it runs →