Skip to content
localmodel.run

Device profile · iOS

Best local LLMs for iPhone 17 Pro

iPhone 17 Pro has ~8 GB usable for model weights and runs 35 of 67 popular models. Best tool: Apple Foundation Models.

Usable memory
~8 GB
Models run
35
Too large
32
Top pick
4B
Top pick Q4_K_M
Gemma 3 4B Yes

Runs at Q4_K_M using ~3.8 GB of ~8 GB usable. You have room for Q8_0 for higher quality.

Runs on iPhone 17 Pro

Compatible models 35 total

Too large for this device

DeepSeek R1DeepSeek V3Qwen3 235B A22Bgpt-oss 120BLlama 4 ScoutSarvam-105BQwen2.5 72BLlama 3.3 70BMixtral 8x7BCommand R 35BYi 1.5 34BQwen2.5 32BQwen3 32BDeepSeek-R1-Distill-Qwen 32BQwen2.5 Coder 32BGranite 4.0 H SmallQwen3 30B-A3BSarvam-30BGemma 2 27BGemma 3 27BMistral Small 3 24BSarvam-M 24Bgpt-oss 20BDeepSeek-V2-LitePhi-4 14BQwen2.5 14BQwen3 14BDeepSeek-R1-Distill-Qwen 14BQwen2.5 Coder 14BMistral Nemo 12BGemma 3 12BLlama 3.2 Vision 11B

Best way to run models on iOS

Runtime guide iOS

Beginner: Apple Foundation Models, Built into iOS 26, ~3B on-device model, zero download, fully private.

Power user: PocketPal AI, Run any GGUF from HuggingFace fully offline.

Phones realistically run 1B-4B class models. Anything larger thermally throttles or OOMs.

Full iOS tool guide →

FAQ

What is the best local LLM for iPhone 17 Pro?

Gemma 3 4B is the strongest model that runs comfortably, using ~3.8 GB at Q4_K_M of the ~8 GB usable on iPhone 17 Pro.

How much of iPhone 17 Pro's memory can I use for a model?

About 8 GB. On a CPU-only machine, leave headroom for the OS and apps.

Which tool should I use on iOS?

Apple Foundation Models (Built into iOS 26, ~3B on-device model, zero download, fully private.) or PocketPal AI for speed. Phones realistically run 1B-4B class models. Anything larger thermally throttles or OOMs.

Sources

Memory figures are estimates. See methodology.