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.

Your device
Use
SmolLM2 360MRuns great
360M · 0.3 GB · 8K

Tiny and instant. Good for quick rewrites and simple questions on any iPhone.

SmolLM2 360M
Everyday chatOffline & travel
View details
Gemma 3 1BRuns great
1B · 0.8 GB · 32K

Google's smallest Gemma. Quick replies in many languages.

Gemma 3 1B
Everyday chatMultilingualOffline & travel
View details
Llama 3.2 1BRuns great
1.2B · 0.8 GB · 128K

Meta's smallest Llama. Quick and light.

Llama 3.2 1B
Everyday chatMultilingualOffline & travel
View details
Dolphin 3.0 Qwen2.5 1.5BRuns great
1.5B · 1.0 GB · 32K

The smallest Dolphin: under 1 GB, so it runs on nearly every iPhone that QUIET Ai supports.

bartowski/Dolphin3.0-Qwen2.5-1.5B-GGUF
Everyday chatOffline & travelUncensored
View details
SmolLM2 1.7BRuns great
1.7B · 1.1 GB · 8K

Small, fast, and surprisingly capable for everyday writing help.

SmolLM2 1.7B
Everyday chatOffline & travel
View details
Qwen3 1.7BRuns great
1.7B · 1.1 GB · 40K

Small model that can think step by step before answering.

Qwen3 1.7B
Everyday chatMultilingualOffline & travelReasoning
View details
DeepSeek R1 1.5BRuns great
1.8B · 1.1 GB · 128K

Thinks out loud before answering. Tiny version of DeepSeek R1.

DeepSeek R1 1.5B
Offline & travelReasoning
View details
Qwen2.5 Coder 3BRuns great
3.1B · 1.9 GB · 32K

Writes and explains code. Small enough for most iPhones.

Qwen2.5 Coder 3B
CodingOffline & travel
View details
Dolphin 3.0 Qwen2.5 3BRuns great
3.1B · 1.9 GB · 32K

Dolphin's few-refusals tuning on Qwen2.5 3B. Quick on any recent iPhone and good in many languages.

bartowski/Dolphin3.0-Qwen2.5-3b-GGUF
Everyday chatMultilingualOffline & travelUncensored
View details
Qwen2.5 3B Instruct AbliteratedRuns great
3.1B · 1.9 GB · 32K

Qwen2.5 3B with refusals removed. Small, fast and multilingual.

mradermacher/Qwen2.5-3B-Instruct-abliterated-GGUF
AbliteratedEveryday chatMultilingualOffline & travelUncensored
View details
Llama 3.2 3BRuns great
3.2B · 2.0 GB · 128K

A well-rounded Llama that runs on most iPhones.

Llama 3.2 3B
Everyday chatMultilingualOffline & travel
View details
Dolphin 3.0 Llama 3.2 3BRuns great
3.2B · 2.0 GB · 128K

The small Dolphin. Same few-refusals tuning, light enough for most recent iPhones.

bartowski/Dolphin3.0-Llama3.2-3B-GGUF
Everyday chatOffline & travelUncensored
View details
Hermes 3 Llama 3.2 3BRuns great
3.2B · 2.0 GB · 128K

The compact Hermes 3 for stories and characters on a phone with less memory.

bartowski/Hermes-3-Llama-3.2-3B-GGUF
Everyday chatOffline & travelStories & charactersUncensored
View details
Phi-4 miniRuns great
3.8B · 2.5 GB · 128K

Microsoft's small model, good at math and structured answers.

Phi-4 mini
CodingEveryday chatOffline & travelReasoning
View details
Phi-4 mini AbliteratedRuns great
3.8B · 2.5 GB · 128K

Microsoft's Phi-4 mini with refusals removed. Strong at reasoning and maths for its size.

mradermacher/Phi-4-mini-instruct-abliterated-GGUF
AbliteratedEveryday chatOffline & travelReasoningUncensored
View details
Qwen3 4BRuns great
4B · 2.5 GB · 40K

Strong reasoning for its size. Thinking can be turned on or off.

Qwen3 4B
CodingEveryday chatMultilingualOffline & travelReasoning
View details
Qwen3 4B AbliteratedRuns great
4B · 2.5 GB · 40K

Qwen3 4B with refusals removed. Step-by-step thinking in a size that suits 8 GB iPhones.

mradermacher/Huihui-Qwen3-4B-abliterated-v2-GGUF
AbliteratedMultilingualOffline & travelReasoningUncensored
View details
Gemma 3 4BRuns great
4.3B · 2.5 GB · 128K

Google's compact all-rounder. Fast, multilingual, can look at photos.

Gemma 3 4B
Everyday chatMultilingualOffline & travelPhotos
View details
Gemma 3 4B AbliteratedRuns great
4.3B · 2.5 GB · 128K

Google's Gemma 3 4B with refusals removed by Maxime Labonne. Small, fast and multilingual.

mlabonne/gemma-3-4b-it-abliterated-GGUF
AbliteratedEveryday chatMultilingualOffline & travelUncensored
View details
Gemma 3n E2BRuns well
5.4B · 3.0 GB · 32K

Built for phones. Uses memory like a 2B model.

Gemma 3n E2B
Everyday chatMultilingual
View details
Gemma 3n E4BTight: close other apps
6.9B · 4.5 GB · 32K

Built for phones. Uses memory like a 4B model with better answers.

Gemma 3n E4B
Everyday chatMultilingual
View details
Mistral 7BTight: close other apps
7.2B · 4.4 GB · 32K

A classic 7B model with a direct style.

Mistral 7B
Everyday chat
View details
Hermes 2 Pro Mistral 7BTight: close other apps
7.2B · 4.4 GB · 32K

A Mistral 7B tuned by Nous Research for open conversation and structured answers. Apache 2.0, so there are few strings attached.

NousResearch/Hermes-2-Pro-Mistral-7B-GGUF
Everyday chatStories & charactersUncensored
View details
Dolphin 2.9.3 Mistral 7BTight: close other apps
7.2B · 4.4 GB · 32K

The classic Dolphin on Mistral 7B: follows the system prompt, with a 32K context for long chats.

bartowski/dolphin-2.9.3-mistral-7B-32k-GGUF
Everyday chatStories & charactersUncensored
View details
Mistral 7B Instruct v0.3 AbliteratedTight: close other apps
7.2B · 4.4 GB · 32K

Mistral 7B v0.3 with refusals removed. A dependable all-rounder under Apache 2.0.

mradermacher/Mistral-7B-Instruct-v0.3-abliterated-GGUF
AbliteratedEveryday chatUncensored
View details
Qwen2.5 Coder 7BTight: close other apps
7.6B · 4.7 GB · 32K

A capable coding assistant for Pro iPhones.

Qwen2.5 Coder 7B
Coding
View details
DeepSeek R1 7BTight: close other apps
7.6B · 4.7 GB · 128K

Careful step-by-step reasoning for math and logic.

DeepSeek R1 7B
Everyday chatReasoning
View details
Qwen2.5 7B Instruct AbliteratedTight: close other apps
7.6B · 4.7 GB · 32K

Qwen2.5 7B with refusals removed. A strong all-rounder in more than 25 languages.

mradermacher/Qwen2.5-7B-Instruct-abliterated-GGUF
AbliteratedEveryday chatMultilingualUncensored
View details
Qwen2.5 Coder 7B AbliteratedTight: close other apps
7.6B · 4.7 GB · 32K

The Qwen2.5 coding model without refusals: security research, scripts and code the original declines to write.

bartowski/Qwen2.5-Coder-7B-Instruct-abliterated-GGUF
AbliteratedCodingUncensored
View details
DeepSeek R1 Llama 8BTight: close other apps
8B · 4.9 GB · 128K

DeepSeek R1 reasoning on a Llama base.

DeepSeek R1 Llama 8B
Everyday chatReasoning
View details
Dolphin 3.0 Llama 3.1 8BTight: close other apps
8B · 4.9 GB · 128K

A general assistant tuned to follow your system prompt instead of a built-in rulebook. Few refusals, strong at writing and code.

dphn/Dolphin3.0-Llama3.1-8B-GGUF
CodingEveryday chatUncensored
View details
Dolphin 3.0 Llama 3.1 8B AbliteratedTight: close other apps
8B · 4.9 GB · 128K

Dolphin 3.0 with its remaining refusal behaviour removed by abliteration, a technique that edits the model's weights rather than its prompt.

mradermacher/Dolphin3.0-Llama3.1-8B-abliterated-GGUF
AbliteratedEveryday chatUncensored
View details
Hermes 3 Llama 3.1 8BTight: close other apps
8B · 4.9 GB · 128K

Nous Research's steerable assistant: long conversations, characters and creative writing, and it sticks to the system prompt.

NousResearch/Hermes-3-Llama-3.1-8B-GGUF
Everyday chatStories & charactersUncensored
View details
Llama 3.1 8B Instruct AbliteratedTight: close other apps
8B · 4.9 GB · 128K

Meta's Llama 3.1 8B with refusals removed by Maxime Labonne. One of the most downloaded abliterated models.

mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated-GGUF
AbliteratedEveryday chatUncensored
View details
DeepSeek R1 Distill Llama 8B AbliteratedTight: close other apps
8B · 4.9 GB · 128K

The DeepSeek R1 reasoning model (Llama 8B distill) with refusals removed. Shows its thinking before it answers.

mradermacher/DeepSeek-R1-Distill-Llama-8B-abliterated-GGUF
AbliteratedReasoningUncensored
View details
Qwen3 8BTight: close other apps
8.2B · 5.0 GB · 40K

The best answers that fit on a phone. Needs a Pro iPhone.

Qwen3 8B
CodingEveryday chatMultilingualReasoning
View details
Qwen3 8B AbliteratedTight: close other apps
8.2B · 5.0 GB · 40K

Qwen3 8B with refusals removed by abliteration. Keeps Qwen3's step-by-step thinking and many languages.

mradermacher/Huihui-Qwen3-8B-abliterated-v2-GGUF
AbliteratedMultilingualReasoningUncensored
View details
Josiefied Qwen3 8B AbliteratedTight: close other apps
8.2B · 5.0 GB · 40K

Qwen3 8B abliterated and then tuned to be a direct, helpful assistant. Thinks step by step.

mradermacher/Josiefied-Qwen3-8B-abliterated-v1-GGUF
AbliteratedEveryday chatReasoningUncensored
View details

Which group is my device in?

iPhone · 6 GBiPhone 13 Pro, 14, 14 Pro, 15, 15 Plus
iPhone · 8 GBiPhone 15 Pro, 16 series, 17, 16e
iPhone · 12 GBiPhone 17 Pro, 17 Pro Max, iPhone Air
iPad · 8 GBiPad Air M1–M3, iPad mini (A17 Pro), iPad Pro M4 256/512 GB
iPad · 16 GBiPad Pro M4 / M5 with 1 TB or 2 TB