Models /Llama 3.2 1B Instruct /Can I run it?

Compatibility check

Can I run Llama 3.2 1B Instruct on Android phone · 6 GB?

Yes — it runs.best quant:

Decode speed

17 tok/sest

Usable context

33K

Memory

3 GB

Fits in memory17 tok/sest · 33K ctx

Fits in memory15 tok/sest · 33K ctx

Fits in memory10 tok/sest · 16K ctx

What is quantisation? →

Llama 3.2 1B Instruct

1.2B · full specs & benchmarks →

Android phone · 6 GB

3 GB · everything it runs →