aicanrun

AI Models for iPhone 14 — What runs on 6GB

16 great · 11 slow · 82 won't fit
Chip
Apple A15 Bionic
Memory bandwidth
34.1 GB/s
NPU
15.8 TOPS
RAM options
6 GB
Usable for models
~3.9 GB
Year
2022

Specs checked against manufacturer and public documentation on .

What runs on the iPhone 14

All 109 models at their recommended quant, on the 6GB configuration. Select any row for the full report.

ModelParamsQuantNeedsSpeedVerdict
Qwen3 0.6B0.6BQ8_01.3 GB~25.6 tokens/s✓ Runs great
Llama 3.2 1B1.2BQ4_K_M1.5 GB~19.2 tokens/s✓ Runs great
Gemma 3 1B1BQ4_K_M1.5 GB~19.2 tokens/s✓ Runs great
Ternary Bonsai 1.7B1.7BQ2_01.2 GB~30.7 tokens/s✓ Runs great
OvisOCR2 0.8B0.8BQ4_K_M1.3 GB~25.6 tokens/s✓ Runs great
OneJev 0.8B0.8BQ4_K_M1.4 GB~21.9 tokens/s✓ Runs great
DeepSeek R1 Distill 1.5B1.8BQ4_K_M1.9 GB~14 tokens/s✓ Runs great
SmolLM2 1.7B1.7BQ4_K_M1.9 GB~14 tokens/s✓ Runs great
Ternary Bonsai 4B4BQ2_02 GB~14 tokens/s✓ Runs great
Qwen 3.5 2B2BQ4_K_M2.1 GB~11.8 tokens/s✓ Runs great
MiniCPM5-2B2.52BQ4_K_M2.5 GB~9.6 tokens/s✓ Runs great
LFM2.5 2.6B2.7BQ4_K_M2.6 GB~9 tokens/s✓ Runs great
LFM2.5-VL 3B3.1BQ4_K_M2.6 GB~9 tokens/s✓ Runs great
Qwen3 1.7B1.7BQ8_02.6 GB~8.5 tokens/s✓ Runs great
G9v3 3B3BQ4_K_M2.8 GB~8.1 tokens/s✓ Runs great
SmolLM3 3B3.1BQ4_K_M2.8 GB~8.1 tokens/s✓ Runs great
Llama 3.2 3B3.2BQ4_K_M2.9 GB~7.7 tokens/s! Runs, barely
Ministral 3 3B3BQ4_K_M3 GB~7.3 tokens/s! Runs, barely
Granite 4.2 3B3BQ4_K_M3.1 GB~7 tokens/s! Runs, barely
Ternary Bonsai 8B8BQ2_03.5 GB~7 tokens/s! Runs, barely
Qwen3 4B4BQ4_K_M3.5 GB~6.1 tokens/s! Runs, barely
Gemma 3 4B4.3BQ4_K_M3.5 GB~6.1 tokens/s! Runs, barely
Phi-4 Mini 3.8B3.8BQ4_K_M3.5 GB~6.1 tokens/s! Runs, barely
Qwen 3.5 4B4BQ4_K_M3.7 GB~5.7 tokens/s! Runs, barely
Agents-A1 4B4BQ4_K_M3.7 GB~5.7 tokens/s! Runs, barely
Nanbeige 4.2 3B4.2BQ4_K_M3.7 GB~5.7 tokens/s! Runs, barely
Nemotron 3 Nano 4B4BQ4_K_M3.8 GB~5.5 tokens/s! Runs, barely
AREX Turbo 4B4.5BQ4_K_M4 GB—✕ Won't fit
Fara 1.5 4B4.5BQ4_K_M4 GB—✕ Won't fit
Gemma 4 E2B2BQ4_K_M4 GB—✕ Won't fit
OneJev 4B4BQ4_K_M4.1 GB—✕ Won't fit
Bonsai 27B (1-bit)27BQ1_04.8 GB—✕ Won't fit
Mistral 7B v0.37.2BQ4_K_M5.7 GB—✕ Won't fit
DeepSeek R1 Distill 7B7.6BQ4_K_M6.1 GB—✕ Won't fit
Gemma 4 E4B4BQ4_K_M6.1 GB—✕ Won't fit
Llama 3.1 8B8BQ4_K_M6.3 GB—✕ Won't fit
Ministral 8B8BQ4_K_M6.3 GB—✕ Won't fit
Ling 3.0 Tiny7.9BQ4_K_M6.3 GB—✕ Won't fit
Qwen3 8B8.2BQ4_K_M6.4 GB—✕ Won't fit
Ministral 3 8B8BQ4_K_M6.6 GB—✕ Won't fit
LFM2.5 8B-A1B8BQ4_K_M6.6 GB—✕ Won't fit
Tini Cybersec 8B-A1B8.5BQ4_K_M6.7 GB—✕ Won't fit
Granite 4.2 8B8BQ4_K_M6.7 GB—✕ Won't fit
Qwen 3.5 9B9BQ4_K_M7.2 GB—✕ Won't fit
Ornith 1.0 9B9BQ4_K_M7.1 GB—✕ Won't fit
Qwythos 9B v29BQ4_K_M7.2 GB—✕ Won't fit
OneJev 9B9BQ4_K_M7.1 GB—✕ Won't fit
GRM 3.2 Cliff 9B9.4BQ4_K_M7.5 GB—✕ Won't fit
grug 9B (ProCreations)9.4BQ4_K_M7.5 GB—✕ Won't fit
Fara 1.5 9B9.4BQ4_K_M7.5 GB—✕ Won't fit
UI-Mate 9B9BQ4_K_M7.4 GB—✕ Won't fit
LensVLM 9B9.4BQ4_K_M7.3 GB—✕ Won't fit
Qwen3 14B14.8BQ4_K_M11.1 GB—✕ Won't fit
Qwen3 30B A3B30.5BQ4_K_M22.3 GB—✕ Won't fit
Gemma 3 12B12.2BQ4_K_M9.1 GB—✕ Won't fit
Phi-4 14B14.7BQ4_K_M11.2 GB—✕ Won't fit
MiMo V2.6 Distill Qwen 9B9.4BQ8_011.2 GB—✕ Won't fit
MiMo V2.6 Flash MOPD309BQ2_K154.7 GB—✕ Won't fit
Qwen 3.5 27B27BQ4_K_M20 GB—✕ Won't fit
Qwen 3.5 35B-A3B35BQ4_K_M26.2 GB—✕ Won't fit
Qwen 3.6 27B27BQ4_K_M18.5 GB—✕ Won't fit
Qwen 3.6 35B-A3B35BQ4_K_M23.9 GB—✕ Won't fit
Gemma 4 12B12BQ4_08.8 GB—✕ Won't fit
Gemma 4 26B-A4B26BQ4_017.5 GB—✕ Won't fit
Ternary Bonsai 27B27BQ2_08.4 GB—✕ Won't fit
Nemotron 3 Nano 30B-A3B30BQ4_K_M28.5 GB—✕ Won't fit
Nemotron 3 Nano Omni 30B-A3B31BQ4_K_M26.3 GB—✕ Won't fit
Nemotron 3.5 Lightning 30B-A3B30BQ8_035.9 GB—✕ Won't fit
Ministral 3 14B14BQ4_K_M10.2 GB—✕ Won't fit
GPT-OSS 20B21BMXFP414.8 GB—✕ Won't fit
Ornith 1.0 35B-A3B35BQ4_K_M25.3 GB—✕ Won't fit
Grug 12B12BQ4_K_M9.5 GB—✕ Won't fit
XYZ-Aquila mini 35B-A3B35BQ4_K_M25.5 GB—✕ Won't fit
Holo4 35B-A3B35BQ4_K_M25.4 GB—✕ Won't fit
OneJev 27B27BQ4_K_M19.8 GB—✕ Won't fit
AREX-2 27B27BQ4_K_M20.6 GB—✕ Won't fit
Salience 1.5 Flash30BQ4_K_M22.3 GB—✕ Won't fit
Fara 1.5 27B27BQ4_K_M20.9 GB—✕ Won't fit
KAT-Coder V2.5 Dev35BQ4_K_M25.5 GB—✕ Won't fit
BigBang V1 36B-A3B36BQ4_K_M26.1 GB—✕ Won't fit
Muse Glimmer 30B29.6BK_QUANT_17GB20.3 GB—✕ Won't fit
Qwen3.8 27B27BQ4_K_M20.8 GB—✕ Won't fit
Qwen3.8 2.4T-A95B2400BIQ4_XS1377.4 GB—✕ Won't fit
UI-Mate 27B27BQ4_K_M20.9 GB—✕ Won't fit
GLM-4.5V106BQ4_K_M74.8 GB—✕ Won't fit
GLM-4.5-Air106BQ4_K_M74.8 GB—✕ Won't fit
Granite 4.2 30B30BQ4_K_M21.3 GB—✕ Won't fit
Apodex 1.1 Mini35BQ4_K_M26 GB—✕ Won't fit
Ling 3.0 Flash124BQ4_K_M82.3 GB—✕ Won't fit
Ling 3.0 Flash Fin124BQ4_K_M91 GB—✕ Won't fit
Ling 3.0 Flash VL124.85BQ4_K_M92 GB—✕ Won't fit
Qwen3.8-27B-pi27.8BQ4_K_M19.9 GB—✕ Won't fit
Swift 1.5 Qwen3.8 27B27.8BQ4_K_M20.8 GB—✕ Won't fit
Swift 1.5 Qwen3.8 Flash Next125BQ2_079.2 GB—✕ Won't fit
Qwen3.8-Flash-Next125BIQ4_XS107.7 GB—✕ Won't fit
GLM-5.3744BQ4_K_XL543.3 GB—✕ Won't fit
GLM-5.3-Flash320BQ4_K_XL232.7 GB—✕ Won't fit
Llama 3.3 70B70BQ4_K_M50.1 GB—✕ Won't fit
Qwen3 32B32.8BQ4_K_M23.7 GB—✕ Won't fit
Ornith 1.0 397B397BQ4_K_M285.6 GB—✕ Won't fit
Gemma 4 31B31BQ4_K_M22 GB—✕ Won't fit
Hunyuan 3 (Hy3)298.8BQ4_K_M212.8 GB—✕ Won't fit
DeepSeek V4 Flash 0731284BQ4_K_XL163.6 GB—✕ Won't fit
DeepSeek V4 Flash Vision Exp284BQ4_K_XL183.3 GB—✕ Won't fit
Inkling952.4BQ8_0966.9 GB—✕ Won't fit
Inkling Small276BQ4_K_M190.5 GB—✕ Won't fit
LongCat Flash Chat561.9BIQ1_S159.6 GB—✕ Won't fit
Laguna XS 2.133BQ4_K_M24.2 GB—✕ Won't fit
Laguna S 2.1118BQ4_K_M109.7 GB—✕ Won't fit

~ = bandwidth-based estimate · ✓ = measured on real hardware

Best model by use case

Best for Chat
Qwen3 0.6B

Top everyday assistant & writing pick here — ~25.6 tokens/s at Q8_0, using 1.3 of ~3.9GB.

Best for Coding
MiniCPM5-2B

Top code completion & explain-this pick here — ~9.6 tokens/s at Q4_K_M, using 2.5 of ~3.9GB.

Best for Reasoning
OneJev 0.8B

Top math & step-by-step thinking pick here — ~21.9 tokens/s at Q4_K_M, using 1.4 of ~3.9GB.

FAQ

What is the biggest AI model the iPhone 14 can run?

Ternary Bonsai 8B (8B parameters) at Q2_0 — it needs 3.5GB of the ~3.9GB usable on the 6GB iPhone 14, at ~7 tokens/s.

How much of the iPhone 14's 6GB RAM can AI models actually use?

About 3.9GB. iOS caps a single app at roughly 65% of total RAM, so of the 6GB about 3.9GB is actually available to a model.

Can the iPhone 14 run Llama 3.1 8B?

Not at Q4_K_M: it needs 6.3GB but the iPhone 14 only has ~3.9GB usable. Try a smaller model like Qwen3 0.6B.

How fast is local AI on the iPhone 14?

The Apple A15 Bionic has 34.1GB/s of memory bandwidth, which is what decode speed scales with. Small models like Ternary Bonsai 1.7B reach ~30.7 tokens/s; larger 7–14B models land in the single digits. Anything above ~8 tokens/s feels smooth for chat.

Which quantization should I use on the iPhone 14?

Q4_K_M is the size/quality sweet spot for most models. For example, Qwen3 0.6B at Q8_0 takes 1.3GB of memory here. Only drop to Q3 or IQ4 if a model just misses fitting; Q8 rarely pays off on 6GB of RAM.

Is 6GB of RAM enough for local AI?

27 of the 109 models we track fit on the iPhone 14 — 16 run great and 11 run with compromises. 82 models (mostly 12B+) don't fit at their recommended quant.

Other Apple phones

iPhone 16 Pro MaxiPhone 16 ProiPhone 16iPhone 15 ProiPhone 15iPhone 17iPhone AiriPhone 17 ProiPhone 17 Pro MaxiPhone 16eiPhone 17eiPhone 18 ProiPhone 18 Pro MaxiPhone Duo