Technology

I ran a real AI chatbot locally on my iPhone — here’s how it worked

By Amanda Caswell

Copyright tomsguide

I ran a real AI chatbot locally on my iPhone — here’s how it worked

Skip to main content

Tom’s Guide

Newsletters

View Profile

Search Tom’s Guide

You May Like

I Just Created 5 Apps Using GPT-5 And It’s So Easy It Feels Like It Should Be Illegal — Here’s How To Do It

I’ve started using ChatGPT’s incognito mode every time — here’s 4 reasons why and how to do it

5 hidden ChatGPT-5 settings you should enable right now

Phone Insights

Phone Best Picks

Phone Deals

Phone Face-Offs

Phone How-Tos

Phone Reviews

Network Carriers

Android Phones

Google Phones

Motorola Phones

OnePlus Phones

Samsung Phones

Nothing Phone

TV Best Picks

TV Face-Offs

Audio Insights

Audio Best Picks

Audio Deals

Audio Face-Offs

Audio How-Tos

Audio Reviews

Over-Ear Headphones

Bluetooth Speakers

Entertainment

Streaming Devices

Prime Video

Paramount Plus

Playstation

Gaming Peripherals

Connections

Computing Insights

Computing Best Picks

Computing Deals

Computing Face-Offs

Computing How-Tos

Computing News

Computing Reviews

VPN Best Picks

VPN Face-Offs

VPN How-Tos

VPN Reviews

Operating Systems

Malware & Adware

Smart Glasses

Chromebooks

Gaming Laptops

Apple Desktops

Gaming Desktops

Android Tablets

Computing Brands

AI Insights

AI Best Picks

AI Face-Offs

Google Gemini

Apple Intelligence

Mattress Best Picks

Mattress Deals

Mattress Face-Offs

Mattress How-Tos

Mattress News

Mattress Reviews

Mattress Care

Mattress Toppers

Pillows & Bedding

Smartwatches

Fitness Trackers

Smart Rings

Apple Watch

Home Insights

Home Best Picks

Home Face-Offs

Home How-Tos

Home Reviews

Home Topics

Home Appliances

Home Office

Home Security

Home Brands

Popular Brands

View Phones

Phone Insights

Phone Best Picks

Phone Deals

Phone Face-Offs

Phone How-Tos

Phone Reviews

Network Carriers

View Network Carriers

Android Phones

View Android Phones

Google Phones

Motorola Phones

OnePlus Phones

Samsung Phones

Nothing Phone

TV Best Picks

TV Face-Offs

Audio Insights

View Audio Insights

Audio Best Picks

Audio Deals

Audio Face-Offs

Audio How-Tos

Audio Reviews

Headphones

View Headphones

Over-Ear Headphones

View Speakers

Bluetooth Speakers

Entertainment

View Entertainment

View Streaming

Streaming Devices

Prime Video

Paramount Plus

View Gaming

Playstation

Gaming Peripherals

Word Games

Connections

View Computing

Computing Insights

Computing Best Picks

Computing Deals

Computing Face-Offs

Computing How-Tos

Computing News

Computing Reviews

VPN Best Picks

VPN Face-Offs

VPN How-Tos

VPN Reviews

View Hardware

View Software

Operating Systems

View Security

Malware & Adware

View VR & AR

Smart Glasses

View Laptops

Chromebooks

Gaming Laptops

View Desktops

Apple Desktops

Gaming Desktops

View Tablets

Android Tablets

Computing Brands

AI Insights

AI Best Picks

AI Face-Offs

AI Engines

Google Gemini

Apple Intelligence

View Wellness

Mattresses

View Mattresses

Mattress Best Picks

Mattress Deals

Mattress Face-Offs

Mattress How-Tos

Mattress News

Mattress Reviews

Mattress Care

Mattress Toppers

Pillows & Bedding

View Fitness

Smartwatches

Fitness Trackers

Smart Rings

Apple Watch

Home Insights

Home Best Picks

Home Face-Offs

Home How-Tos

Home Reviews

Home Topics

Home Appliances

Home Office

Home Security

View Outdoors

Home Brands

Popular Brands

Apple Event

iPhone 17 Pro
The World in 2035
Wordle Today
Best laptops

Best Mattress

Don’t miss these

I Just Created 5 Apps Using GPT-5 And It’s So Easy It Feels Like It Should Be Illegal — Here’s How To Do It

I’ve started using ChatGPT’s incognito mode every time — here’s 4 reasons why and how to do it

5 hidden ChatGPT-5 settings you should enable right now

I asked ChatGPT-5 to take me behind the scenes of its brain — this is what I learned

ChatGPT-5 features — here’s the 5 upgrades I would try first

OpenAI’s new ChatGPT agent is here — 5 features that change everything

This overlooked GPT-5 upgrade is my favorite — and even as a power user, it blew me away

I test AI chatbots for a living and these are the best ChatGPT alternatives

ChatGPT-5 is here — 7 biggest upgrades you need to know

GPT-4 isn’t gone — here’s how to use it for free right now

I’ve been testing ChatGPT-5 — and these 3 features are absolutely brilliant

I just tested ChatGPT-5 vs Deepseek with 9 prompts — and there’s a clear winner

I test AI for a living — here’s 7 prompts for getting the most out of ChatGPT-5

Forget ChatGPT — 4 reasons why you should try this chatbot you’ve (probably) never heard of

I test AI for a living — here’s what I tell ChatGPT (and what I never will)

I ran a real AI chatbot locally on my iPhone — here’s how it worked

Amanda Caswell

10 September 2025

Free and private are just a few of the reasons to try it

When you purchase through links on our site, we may earn an affiliate commission. Here’s how it works.

(Image credit: Shutterstock)

AI chatbots like ChatGPT and Gemini usually need the cloud to function. However, what if you could run an entire large language model (LLM) right on your iPhone without a subscription, an internet connection and without any data leaving your device? Thanks to a handful of apps and lightweight, compressed models, you actually can.

I tried it out, and here’s what you need to know.
Running AI locally on iPhone

(Image credit: Future)
You can now run open-source models like Llama and Qwen directly on iOS. These models are slimmed down using a process called quantization, which compresses them to fit into mobile memory without completely breaking performance.

You may like

I Just Created 5 Apps Using GPT-5 And It’s So Easy It Feels Like It Should Be Illegal — Here’s How To Do It

I’ve started using ChatGPT’s incognito mode every time — here’s 4 reasons why and how to do it

5 hidden ChatGPT-5 settings you should enable right now

The catch: performance depends heavily on your hardware. An iPhone 15 Pro or 15 Pro Max with Apple’s latest chip can load models up to 7B or 8B parameters (like Llama 3.1 8B), while older phones are better suited for smaller 1–3B parameter models.

The apps that make it possible

(Image credit: Tom’s Guide)

LLM Farm (free): The easiest way to start. You can download a small model (like Phi-3.5 Instruct) and run it offline with just a tap. It’s surprisingly smooth for quick Q&A.
MLC Chat (free): This is the one I used. I would have used LLM Farm but for some reason the Apple App Store wasn’t giving me the option to download it. Since this one was free, I went for it and it worked just as well.
Private LLM (community project): This is more of a DIY option and not for the casual user. This one has detailed guides for loading models like Llama 3.1 and Qwen on your iPhone. If you like to tinker, definitely give it a shot.
Apollo (paid): I’ve heard good things but have not tried this app myself. Let me know in the comments what you think of this privacy-focused app.
How to locally run the model

(Image credit: Getty Images)
Once you’ve downloaded your app of choice, open the app. From there, browse the built-in model list and choose one (e.g., Phi-3.5 Instruct Q4 quantized). I chose Qwen 2.5 for no other reason except that I haven’t used it for awhile.

Once you download it, you will see the model on your device (anywhere from a few hundred MB to several GB depending on size). From there, just start chatting.
You’ll want to keep expectations realistic; this is not the time to ask for deep dives or long step-by-step plans. Keep the following in mind:

Speed: Small models (1–3B) respond faster; big models can take seconds per token.
Context: Don’t paste entire essays; keep prompts shorter.
Output: Local LLMs may be less polished than ChatGPT, but they’re useful for notes, summaries, Q&A, and lightweight drafting.
I had fun trying a few prompts. Nothing fancy; my goal was just to see the type of responses I got from the local request. One thing you’ll notice right away is the speed. It’s incredible how fast the LLM responds.

I tried the following prompts and overall, I was impressed.

Sign up to get the BEST of Tom’s Guide direct to your inbox.
Get instant access to breaking news, the hottest reviews, great deals and helpful tips.
Contact me with news and offers from other Future brandsReceive email from us on behalf of our trusted partners or sponsorsBy submitting your information you agree to the Terms & Conditions and Privacy Policy and are aged 16 or over.

“Summarize the Declaration of Independence in three bullet points.”
“Write a short bedtime story about a robot and a cat.”
“Give me three dinner ideas using chicken, rice, and broccoli.”
Running a local LLM isn’t the same as chatting with ChatGPT-5. It definitely feels streamlined and raw. If you try this, remember to keep your prompts short because the context windows are much more limited than when using the regular version of the chatbots. Responses will feel slower if you overload the local LLM.
Why would you do this?

(Image credit: Meta)

No subscription fees. You are not burning credits just to experiment.
Privacy built in. Everything stays on your device.
Surprisingly versatile. I was blown away by how much the mini model could handle. Every time I pushed the limits, it was able to tackle the challenege easily.
Final thoughts
If you have an iPhone 15 or greater and are curious about what AI looks like ‘under the hood,’ go for it. LLM Farm or MLCChat are fast and free ways to get to get started. For privacy hawks, Apollo is worth a look. And if you’re more of a tinkerer, Private LLM lets you go deep into custom setups.

Just remember that these are not the full-power chatbots you’re used to, so don’t expect outputs like ChatGPT. But, it is pretty cool and feels futuristic to run your own AI on your iPhone.

Follow Tom’s Guide on Google News to get our up-to-date news, how-tos, and reviews in your feeds. Make sure to click the Follow button.
More from Tom’s Guide

Nano Banana just broke the internet with these viral trends — I tried these 5 prompts and I’m blown away
OpenAI launches ‘OpenAI for Science’ initiative to build the ‘next great scientific instrument’ – here’s what we know
ChatGPT just quietly rolled out a game-changing upgrade — here’s why I’m already obsessed with it

Back to Mobile Cell Phones

Storage Size

Refurbished

Showing 10 of 214 deals

Apple iPhone 16 Pro Max

(256GB White)

$1,379View Deal

Apple iPhone 16

(128GB Pink)

$23.06View Deal

Apple iPhone 16 Plus

(128GB Black)

$1,109View Deal

Apple Apple iPhone 16 Pro

$59.95View Deal

Apple iPhone 15

$729.99View Deal

Apple iPhone 16 Pro Max

$1,199.99View Deal

Apple iPhone 16

$829View Deal

Apple iPhone 16 Plus

$929.99View Deal

Apple Apple iPhone 16 Pro

$2.14View Deal

Apple iPhone 15

$729View Deal

See more AI How To

Amanda Caswell

Social Links Navigation

Amanda Caswell is an award-winning journalist, bestselling YA author, and one of today’s leading voices in AI and technology. A celebrated contributor to various news outlets, her sharp insights and relatable storytelling have earned her a loyal readership. Amanda’s work has been recognized with prestigious honors, including outstanding contribution to media.
Known for her ability to bring clarity to even the most complex topics, Amanda seamlessly blends innovation and creativity, inspiring readers to embrace the power of AI and emerging technologies. As a certified prompt engineer, she continues to push the boundaries of how humans and AI can work together.
Beyond her journalism career, Amanda is a bestselling author of science fiction books for young readers, where she channels her passion for storytelling into inspiring the next generation. A long-distance runner and mom of three, Amanda’s writing reflects her authenticity, natural curiosity, and heartfelt connection to everyday life — making her not just a journalist, but a trusted guide in the ever-evolving world of technology.

You must confirm your public display name before commenting

Please logout and then login again, you will then be prompted to enter your display name.

I Just Created 5 Apps Using GPT-5 And It’s So Easy It Feels Like It Should Be Illegal — Here’s How To Do It

I’ve started using ChatGPT’s incognito mode every time — here’s 4 reasons why and how to do it

5 hidden ChatGPT-5 settings you should enable right now

I asked ChatGPT-5 to take me behind the scenes of its brain — this is what I learned

ChatGPT-5 features — here’s the 5 upgrades I would try first

OpenAI’s new ChatGPT agent is here — 5 features that change everything

Latest in AI

AI made me a 7-song playlist (plus a bonus track) in 30 minutes — here’s how you can try it free

OpenAI’s bold new project isn’t a chatbot — and it could change science forever

Nano Banana just broke the internet with these viral trends — I tried these 5 prompts and I’m blown away

Gemini’s free tier is capped at 5 prompts — here’s how to get more without upgrading

ChatGPT just quietly rolled out a game-changing upgrade — here’s why I’m already obsessed with it

This new AI voice recorder wants to be your affordable transcription device

Latest in How To

I ran a real AI chatbot locally on my iPhone — here’s how it worked

How to watch South Africa vs Nigeria on FIFA+ — it’s *FREE*

How to watch Sinner vs Alcaraz: live stream US Open 2025 men’s final for free, Trump arrives late

How to watch US Open 2025 women’s final: live stream Sabalenka vs Anisimova online from anywhere

How to watch England vs Australia: Live stream Women’s Rugby World Cup 2025 online from anywhere for FREE

Kazakhstan vs Wales live stream: How to watch 2026 World Cup qualifier online from anywhere for FREE today, team news

LATEST ARTICLES

Don’t buy a new PC for Windows 11 just yet — this lightweight version can save your old Windows 10 PC

This intense survival thriller movie just resurfaced in Prime Video’s top 10 — and it’s based on an incredible true story

An expert trainer says this 7-minute mobility routine reverses hours of damage to your hips, back and shoulders

iPhone 17 launch means some older iPhones have been discontinued — here’s what’s affected

Apple Watch Series 11 is not a blood pressure monitor — here’s how hypertension alerts work

Tom’s Guide is part of Future US Inc, an international media group and leading digital publisher. Visit our corporate site.

Terms and conditions

Contact Future’s experts

Privacy policy

Cookies policy

Accessibility Statement

Advertise with us

Future US, Inc. Full 7th Floor, 130 West 42nd Street,

Please login or signup to comment

Please wait…