Find an AI model for your iPhone or iPad
Every model here runs on the device with QUIET Ai: offline, no account, nothing sent anywhere. Pick your device to see what fits.
Tiny and instant. Good for quick rewrites and simple questions on any iPhone.
Google's smallest Gemma. Quick replies in many languages.
Meta's smallest Llama. Quick and light.
The smallest Dolphin: under 1 GB, so it runs on nearly every iPhone that QUIET Ai supports.
Small, fast, and surprisingly capable for everyday writing help.
Small model that can think step by step before answering.
Thinks out loud before answering. Tiny version of DeepSeek R1.
Writes and explains code. Small enough for most iPhones.
Dolphin's few-refusals tuning on Qwen2.5 3B. Quick on any recent iPhone and good in many languages.
Qwen2.5 3B with refusals removed. Small, fast and multilingual.
A well-rounded Llama that runs on most iPhones.
The small Dolphin. Same few-refusals tuning, light enough for most recent iPhones.
The compact Hermes 3 for stories and characters on a phone with less memory.
Microsoft's small model, good at math and structured answers.
Microsoft's Phi-4 mini with refusals removed. Strong at reasoning and maths for its size.
Strong reasoning for its size. Thinking can be turned on or off.
Qwen3 4B with refusals removed. Step-by-step thinking in a size that suits 8 GB iPhones.
Google's compact all-rounder. Fast, multilingual, can look at photos.
Google's Gemma 3 4B with refusals removed by Maxime Labonne. Small, fast and multilingual.
Built for phones. Uses memory like a 2B model.
Built for phones. Uses memory like a 4B model with better answers.
A classic 7B model with a direct style.
A Mistral 7B tuned by Nous Research for open conversation and structured answers. Apache 2.0, so there are few strings attached.
The classic Dolphin on Mistral 7B: follows the system prompt, with a 32K context for long chats.
Mistral 7B v0.3 with refusals removed. A dependable all-rounder under Apache 2.0.
A capable coding assistant for Pro iPhones.
Careful step-by-step reasoning for math and logic.
Qwen2.5 7B with refusals removed. A strong all-rounder in more than 25 languages.
The Qwen2.5 coding model without refusals: security research, scripts and code the original declines to write.
DeepSeek R1 reasoning on a Llama base.
A general assistant tuned to follow your system prompt instead of a built-in rulebook. Few refusals, strong at writing and code.
Dolphin 3.0 with its remaining refusal behaviour removed by abliteration, a technique that edits the model's weights rather than its prompt.
Nous Research's steerable assistant: long conversations, characters and creative writing, and it sticks to the system prompt.
Meta's Llama 3.1 8B with refusals removed by Maxime Labonne. One of the most downloaded abliterated models.
The DeepSeek R1 reasoning model (Llama 8B distill) with refusals removed. Shows its thinking before it answers.
The best answers that fit on a phone. Needs a Pro iPhone.
Qwen3 8B with refusals removed by abliteration. Keeps Qwen3's step-by-step thinking and many languages.
Qwen3 8B abliterated and then tuned to be a direct, helpful assistant. Thinks step by step.
Which group is my device in?
| iPhone · 6 GB | iPhone 13 Pro, 14, 14 Pro, 15, 15 Plus |
| iPhone · 8 GB | iPhone 15 Pro, 16 series, 17, 16e |
| iPhone · 12 GB | iPhone 17 Pro, 17 Pro Max, iPhone Air |
| iPad · 8 GB | iPad Air M1–M3, iPad mini (A17 Pro), iPad Pro M4 256/512 GB |
| iPad · 16 GB | iPad Pro M4 / M5 with 1 TB or 2 TB |