Skip to content

Rig score · iphone

Device readout 2026-08-03
Rig Score D tier
27%
iPhone 16 Pro · 8 GB
runs 37 of 135 models · biggest Gemma 4 E2B
localmodel.run/rig

iPhone 16 Pro

Runs 37 of 135 models (27%)

Entry, small 1-4B models only.

Biggest it can run: Gemma 4 E2B

Grade
D
Runnable
37
Total
135
Coverage
27%

What iPhone 16 Pro can run

At 8 GB of unified memory, iPhone 16 Pro runs 37 of 135 tracked local models, 27% coverage that earns a D. The largest it handles is Gemma 4 E2B at 5.1B parameters; anything bigger needs more memory or a lower quantization.

On-device models run through apps like PocketPal. Stay under about 4B parameters for usable speed and keep the context short to limit memory.

29 run well 8 tight fit 98 too big

Top models on iPhone 16 Pro

FAQ

What local AI rig score does iPhone 16 Pro get?

iPhone 16 Pro scores D: it runs 37 of 135 tracked local LLMs (27%). The biggest it can run is Gemma 4 E2B.

How big a model can iPhone 16 Pro run?

iPhone 16 Pro runs models up to Gemma 4 E2B (5.1B parameters) at Q4_K_M. Its memory is shared with the system, so leave a few GB for the OS.

Is iPhone 16 Pro good for running local LLMs?

On-device models run through apps like PocketPal. Stay under about 4B parameters for usable speed and keep the context short to limit memory.

Want your own? Check your rig on the homepage →

Score from coverage of 135 tracked models, estimated with our memory methodology.