Device profile · iOS
Best local LLMs for iPhone Air
iPhone Air 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
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 Air
- FN TightFalcon3 10B10B · ~7.5 GB at Q4_K_M
- TightGemma 2 9B9B · ~7.3 GB at Q4_K_M
- GL TightGLM-4 9B9B · ~7.3 GB at Q4_K_M
- TightQwen2.5-VL 7B8.29B · ~7.1 GB at Q4_K_M
- YesLlama 3.1 8B8B · ~6.4 GB at Q4_K_M
- YesQwen3 8B8B · ~6.5 GB at Q4_K_M
- YesDeepSeek-R1-Distill-Llama 8B8B · ~6.4 GB at Q4_K_M
- YesMistral 7B7B · ~5.8 GB at Q4_K_M
- YesQwen2.5 7B7B · ~6.1 GB at Q4_K_M
- YesDeepSeek-R1-Distill-Qwen 7B7B · ~6.1 GB at Q4_K_M
- YesQwen2.5 Coder 7B7B · ~5.8 GB at Q4_K_M
- YesGemma 3 4B4B · ~3.8 GB at Q4_K_M
- YesQwen3 4B4B · ~3.8 GB at Q4_K_M
- YesPhi-3.5-mini 3.8B3.82B · ~3.7 GB at Q4_K_M
- YesPhi-4-mini 3.8B3.8B · ~3.8 GB at Q4_K_M
- YesQwen2.5-VL 3B3.75B · ~4.4 GB at Q4_K_M
- YesQwen2.5 3B3.09B · ~3.3 GB at Q4_K_M
- YesQwen2.5 Coder 3B3.09B · ~3 GB at Q4_K_M
- YesLlama 3.2 3B3B · ~3.2 GB at Q4_K_M
- YesSmolLM3 3B3B · ~3 GB at Q4_K_M
- YesGemma 2 2B2.61B · ~2.9 GB at Q4_K_M
- YesGranite 3.1 2B2.53B · ~2.8 GB at Q4_K_M
- S YesSarvam-1 2B2B · ~2.7 GB at Q4_K_M
- YesSmolLM2 1.7B1.7B · ~2.2 GB at Q4_K_M
- YesQwen3 1.7B1.7B · ~2.4 GB at Q4_K_M
- YesQwen2.5 1.5B1.54B · ~2.2 GB at Q4_K_M
- YesQwen2.5 Coder 1.5B1.54B · ~2 GB at Q4_K_M
- TL YesTinyLlama 1.1B1.1B · ~1.8 GB at Q4_K_M
- YesLlama 3.2 1B1B · ~1.8 GB at Q4_K_M
- YesGemma 3 1B1B · ~1.8 GB at Q4_K_M
- YesQwen3 0.6B0.6B · ~1.5 GB at Q4_K_M
- YesQwen2.5 0.5B0.494B · ~1.5 GB at Q4_K_M
- YesQwen2.5 Coder 0.5B0.494B · ~1.4 GB at Q4_K_M
- YesSmolLM2 360M0.362B · ~1.2 GB at Q4_K_M
- YesSmolLM2 135M0.135B · ~1 GB at Q4_K_M
Too large for this device
Best way to run models on 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 Air?
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 Air.
How much of iPhone Air'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.