• Skip to main content
  • Skip to secondary menu
  • Skip to primary sidebar
The Blog of Jorge de la Cruz

The Blog of Jorge de la Cruz

Everything about VMware, Veeam, InfluxData, Grafana, Zimbra, etc.

  • Home
  • VMWARE
  • VEEAM
    • Veeam Content Recap 2021
    • Veeam v11a
      • Veeam Backup and Replication v11a
    • Veeam Backup for AWS
      • Veeam Backup for AWS v4
    • Veeam Backup for Azure
      • Veeam Backup for Azure v3
    • VeeamON 2021
      • Veeam Announces Support for Red Hat Enterprise Virtualization (RHEV/KVM)
      • Veeam announces enhancements for new versions of Veeam Backup for AWS v4/Azure v3/GVP v2
      • VBO v6 – Self-Service Portal and Native Integration with Azure Archive and AWS S3 Glacier
  • Grafana
    • Part I (Installing InfluxDB, Telegraf and Grafana on Ubuntu 20.04 LTS)
    • Part VIII (Monitoring Veeam using Veeam Enterprise Manager)
    • Part XII (Native Telegraf Plugin for vSphere)
    • Part XIII – Veeam Backup for Microsoft Office 365 v4
    • Part XIV – Veeam Availability Console
    • Part XV – IPMI Monitoring of our ESXi Hosts
    • Part XVI – Performance and Advanced Security of Veeam Backup for Microsoft Office 365
    • Part XVII – Showing Dashboards on Two Monitors Using Raspberry Pi 4
    • Part XIX (Monitoring Veeam with Enterprise Manager) Shell Script
    • Part XXII (Monitoring Cloudflare, include beautiful Maps)
    • Part XXIII (Monitoring WordPress with Jetpack RESTful API)
    • Part XXIV (Monitoring Veeam Backup for Microsoft Azure)
    • Part XXV (Monitoring Power Consumption)
    • Part XXVI (Monitoring Veeam Backup for Nutanix)
    • Part XXVII (Monitoring ReFS and XFS (block-cloning and reflink)
    • Part XXVIII (Monitoring HPE StoreOnce)
    • Part XXIX (Monitoring Pi-hole)
    • Part XXXI (Monitoring Unifi Protect)
    • Part XXXII (Monitoring Veeam ONE – experimental)
    • Part XXXIII (Monitoring NetApp ONTAP)
    • Part XXXIV (Monitoring Runecast)
  • Nutanix
  • ZIMBRA
  • PRTG
  • LINUX
  • MICROSOFT

Jetson: NVIDIA Jetson Orin Nano – How-to run DeepSeek-R1 on Ollama – Local and secure reasoning

10th February 2025 - Written in: linux

Greetings friends, on previous articles, I showed you how to install Ollama and download your first models. A few weeks ago DeepSeek-R1 took the Internet by surprise with it-s incredible reasoning model. You can of course give it a try on the official website or downloading the mobile application. DeepSeek mark a significant step forward in how reinforcement learning (RL) can shape large language models, and the results are really exciting. Let’s break it down on this article.

What is DeepSeek-R1-Zero

Before we jump into the great stuff, let’s start with a brief overview of what DeepSeek-R1-Zero is. We are talking about an AI model trained using large-scale reinforcement learning (RL) alone, with no supervised fine-tuning (SFT) as an initial step. The results are outstanding. The model exhibits strong reasoning skills and naturally develops powerful capabilities like self-verification, reflection, and complex chain-of-thought (CoT) generation. Where before we needed to create this chain-of-thought manually, with DeepSeek-R1 we can observe how to model comes to conclusions and what to do next by itself!

There is a small caveat, DeepSeek-R1-Zero struggles with endless repetition, poor readability, and language mixing. So the guys at DeepSeek achieved an impressive reasoning, which was good as a first step.

What is DeepSeek-R1

To address the limitations mentioned above, and even further refining of the model’s reasoning abilities, these guys introduced DeepSeek-R1. This model incorporates cold-start data before RL, helping to mitigate the readability issues while maintaining the strong reasoning patterns discovered in DeepSeek-R1-Zero. So that is what we can see as GA with DeepSeek-R1, one of the best AI models, delivering performance on par with OpenAI-o1 across math, coding, and reasoning benchmarks.

Open-Source? Secure?

If you have been following this blog, if I can have something open-source vs proprietary, I will chose open-source. Not just that, Since Meta released (leaked) Llama, everything changed in the AI space, where only a few controlled the whole ecosystem.

There has been recently countless number of posts regarding how DeepSeek uses your data, and how much data it collects. I mean, if you know just a little bit about Internet, you should know by now that the phones and the smart speakers listen to the conversations, that Google scans all your Inbox and searches to offer you tailored ads, etc. OpenAI does exactly the same as DeepSeek, but instead of send the data to China, it send it to the United States. Look, I understand the concerns, especially if the questions you are going to ask, or the material you are going to pass is considered sensitive, or you are under some regulations, or of course, sending Intellectual Proprietary material, let’s say your current employer private information.

That is why DeepSeek did it right, as they have open-sourced both DeepSeek-R1-Zero and DeepSeek-R1, along with six distilled models based on Llama and Qwen.

So, my personal recommendation if you want to keep your data secure, please run open source, private and local models as much as you can. Let’s take a look at the distilled models that DeepSeek has released, in the case that you are asking yourselves what a distilled model is: distill models are fine-tuned based on open-source models, using samples generated by DeepSeek-R1.

Model Base Model
DeepSeek-R1-Distill-Qwen-1.5B Qwen2.5-Math-1.5B
DeepSeek-R1-Distill-Qwen-7B Qwen2.5-Math-7B
DeepSeek-R1-Distill-Llama-8B Llama-3.1-8B
DeepSeek-R1-Distill-Qwen-14B Qwen2.5-14B
DeepSeek-R1-Distill-Qwen-32B Qwen2.5-32B
DeepSeek-R1-Distill-Llama-70B Llama-3.3-70B-Instruct

Right, let’s finally unlock the full power of our NVIDIA Jetson Orin Nano and run DeepSeek.

How-to Download and run DeepSeek-R1, securely, and private using Ollama

First, let’s go to the Ollama website to see what models we can download and run for our Jetson Nano:

  • https://ollama.com/library/deepseek-r1

There are a few models, I have tried the 1.5B and 7B ones, if I try running the 8B, it is too much for the unit as the OS it is using some RAM as well. But of course if you have enough RAM/VRAM I would totally recommend 32B onwards. Once we know the model we want, let’s go to our NVIDIA Jetson Nano and run the next:

ollama run deepseek-r1:1.5b

We will see how the model downloads, and that’s it! I mean, this is always so simple that it blows my mind. Let’s login now to our Open WebUI, which I covered as well on previous blog post. And we can now select the model, or models that we want:

Let’s give it a quick try to see if it can help us coding something simple, we will start seeing the reasoning process, with a few little nuggets that reads very cool:

And let’s check the result, it might not be perfect or very complete but the thought process is what we are evaluating. Especially the smaller models, can help whenever you pass a great and simple task to solve at a time. Try the 7B for a much better results.

That’s it for today, I hope you can give this a try, wherever it is DeepSeek, or any other model, as said previously, my recommendation is to always run it locally whenever possible.

Filed Under: linux Tagged With: AI models, AI performance, AI reasoning, AI security, DeepSeek vs OpenAI, DeepSeek-R1, DeepSeek-R1 distill, DeepSeek-R1-Zero, Jetson Nano AI, Llama AI, Ollama AI, open-source AI, private AI, reinforcement learning, run AI locally

Reader Interactions

Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Primary Sidebar

  • E-mail
  • GitHub
  • LinkedIn
  • RSS
  • Twitter
  • YouTube

Posts Calendar

February 2025
M T W T F S S
 12
3456789
10111213141516
17181920212223
2425262728  
« Jan   Mar »

Disclaimer

All opinions expressed on this site are my own and do not represent the opinions of any company I have worked with, am working with, or will be working with.

Copyright © 2025 · The Blog of Jorge de la Cruz