How to Run DeepSeek R1 Locally on Your Phone [2 Methods]

Main Image
  • Like
  • Comment
  • Share

DeepSeek R1 is breaking barriers, not just because it’s open-source but because you can run it anywhere—even on your phone, without it being useless. DeepSeek’s locally run AI models can be as powerful as ChatGPT 4o.

While cloud setups deliver the best performance, running DeepSeek R1 locally on a phone has its own charm. Whether you’re offline, need extra privacy, or just want to reduce dependency on cloud services, this guide will show you how to set it up. 

Sure, not everyone will go this route, but knowing you can run cutting-edge AI in your pocket is mind-blowing. And, the cherry on top is that it’s really simple to do so. Let’s dive in.

Why Run DeepSeek R1 on Your Phone?

Offline access lets you work anywhere without needing the internet. Keeping everything on your device ensures your data stays private and secure. 

It’s convenient for quick AI tasks without logging into cloud services. Plus, you avoid server outages or delays, staying fully in control. While cloud solutions offer better results, local setups give you flexibility and privacy.

ALSO READ: DeepSeek R1 Is Giving OpenAI ChatGPT o1 a Run for Its Money

Prerequisites for Local Installation

To make this work, your device needs some muscle. Here’s what we recommend:

  • RAM: 8 GB (minimum for 8B/14B models).
  • Processor: Powerful SoCs like Snapdragon 8 Gen 2/3, Snapdragon 7+ Gen 3, Dimensity 8400.
  • Storage: 12 GB free space.

Method 1: Termux 

Running DeepSeek R1 on Termux gives full control, but it requires a bit of setup. It also use a terminal interface.

1. Head to Termux’s GitHub page and download the latest APK. Install it and grant necessary permissions.

2. Open Termux and follow these steps:

Clone the repository: 

git clone –depth 1 https://github.com/ollama/ollama.git

cd ollama

Compile the code: 

go generate ./…

go build .

3. Go for quantized models like dseq-r1:8b-q4 to save RAM. Use this command to pull the model:

./ollama run deepseek-r1:8b-q4

4. Start the server with:

./ollama serve &

5. Start using the model using this command:

./ollama run deepseek-r1:8b

>>> “your prompt here”

ALSO SEE: Decoding Nothing’s Latest Cryptic Teaser: Is the Nothing Phone 3a Launching Before the Phone 3?

Method 2: PocketPal (Easy and User-Friendly)

For those who want a plug-and-play option, PocketPal provides an easy way to run Al models on Android and iOS. It’s got a graphical user interface, making it easy to use, even for a layman. Oh, and PocketPal is open source. Follow the steps below.

1. Download PocketPal from the Google Play Store or the App Store. 

2. Open the app and tap on “Go to Models.”

3. Tap the “+” icon and choose “Add from Hugging Face.” This will take you to an expansive list of AI models to choose from.

4. Use the search bar at the bottom and search for “DeepSeek.” 

5. Models with lower parameters (e.g., 1.5B, 7B) are faster but less accurate. Larger models (e.g., 8B) provide better reasoning but need powerful devices. 

6. I recommend going for the smaller models, or based on how much RAM your phone has. Each model has multiple sub-models—you can download multiple models and run them successively. 

7. Once downloaded, go back to the Models page. 

8. Here, you’ll see your models. Tap on “Settings” under the model you just downloaded and adjust the tokens (e.g., 4096 for better context and more text generation).

9. Now, tap on “Load” to get it into action. 

10. Type your prompt. The app’s graphical UI makes interacting smooth and fun. You can switch between models or regenerate responses directly within the app. You can even edit or copy your prompts.

ALSO READ: [Exclusive] Nothing’s 2025 Surprise: Three New Smartphones on the Horizon

Conclusion 

Running DeepSeek R1 locally might not be for everyone, but it’s good to know you have the option. Whether for offline use, privacy, or just because you’re a tech enthusiast, these methods ensure DeepSeek R1 is in your hands, literally. Would you try it out? Let us know.

You can follow Smartprix on Twitter, Facebook, Instagram, and Google News. Visit smartprix.com for the latest tech and auto news, reviews, and guides.

Mehtab AnsariMehtab Ansari
Mehtab Ansari is the Assistant Editor – Features & Reviews at Smartprix, where he writes about smartphones, laptops, audio gear, and everything in between. A computer science student by degree but a tech nerd by heart, he’s been into consumer tech for years and started reviewing products professionally in February 2024. He’s especially into photography and audio, often spending more time testing a smartphone’s camera than he probably should. For him, tech isn’t just work, it’s what he’s always thinking about.

Expertise 

Smartphones, laptops, tablets, monitors, smartwatches, photography, and audio gear. I’ve reviewed over 60 products across these categories on Smartprix in the past year and a half.

Education - Bachelor of Computer Applications – Nizam College, Hyderabad (2022–2025) | Joined Smartprix -February 2024 | Published Reviews & Stories - 723

Related Articles

ImageSony ULT Tower 5, 7, and Max Launched in India, Starting at ₹44,490

Just yesterday, I wrote a story about JBL updating its PartyBox lineup in India. Today, Sony’s has unveiled its second-generation ULT Tower lineup in India just in time for the festive season. Contrary to what I expected, this feels less like an incremental refresh and more like Sony genuinely rethinking what a party speaker should …

ImageQualcomm Announces Snapdragon Sound Elite Gen 2 for AI-Powered Audio Wearables

Qualcomm has announced Snapdragon Sound Elite Gen 2 at Snapdragon Summit 2026. The new platform is built for earbuds, headphones and glasses that can run AI without sending every task to a phone. Qualcomm wants these devices to do more than play music or take calls. They can use AI on the device, connect to …

ImageSamsung Galaxy Watch Ultra 2 Review: Best Rugged Android Smartwatch Made For Enthusiasts

Samsung made a loud statement with the first Galaxy Watch Ultra. That watch was tough but bulky, and it overheated during long GPS sessions. After a month with the Ultra 2, I can see the difference. The Galaxy Watch Ultra 2 is a smart course correction. At $699 or ₹64,999, it’s not a radical redesign. …

ImageThe Foldable iPhone Duo is Finally Here. But Can Apple’s New CEO Sell a $2,000 Phone?

Apple’s September 9 “Surprise and Shine” keynote starts tomorrow at 10:00 AM PT (10:30 PM IST). It breaks the company’s decade-long script. Usually, we know the formula: a sleek prerecorded video, steady spec upgrades, and safe commercial bets. Tomorrow is different. Apple is introducing a new chief executive, entering an entirely new hardware category, and …

ImageAi+ Launches Nova 2, Nova 2 Ultra, and Nova Flip in India, alongside a tablet and several smartwatches and TWS

Ai+ has officially launched the Nova Series in India, bringing three new smartphones along with a tablet and multiple accessories. With this launch, the brand is expanding beyond just phones and is building a full ecosystem that includes audio products, wearables, and a tablet. All devices run on NxtQuantum OS, and the company is also …

Discuss

1 Comment
Carlos Antonio Pinzón
Carlos Antonio Pinzón
@carlos_qemexudi
1 year ago

Excellent method. I just tried it and it worked. My tablet doesn't have the recommended amount of memory, so there is a warning message, but it loads the model and answers queries (very very slowly). I imagine it should work fast on a device with larger RAM.

Reply