LLMap
Models /Llama 3.2 3B Instruct /Can I run it?
Compatibility check

Can I run Llama 3.2 3B Instruct on iPhone 16?

Yes — it runs.best quant:
Decode speed
14 tok/sest
Usable context
33K
Memory
4.4 GB
Fits in memory14 tok/sest · 33K ctx
Fits in memory12 tok/sest · 16K ctx
Too large
What is quantisation? →
Llama 3.2 3B Instruct
3.2B · full specs & benchmarks →
iPhone 16
4.4 GB · everything it runs →