Hi! In this day and age, almost everything is subscription-based. It’s madness: $20/month for ChatGPT, $20/month for Copilot, $20/month for Google Gemini Pro, and more. All of these can add up to a lot of money, especially if you have various needs. This cost can be a barrier for many people, especially those not based in more wealthy countries such as the US. I want to make AI more accessible to everyone. Thus, I’m sharing two ways that you can end this subscription madness by accessing open-source LLMs. Read below, and worry not, because they are all super easy to use.

In today’s rundown:

• Targeted Audience: Non-technical AI users, free stuff lovers, daily AI users.

• AI Tool Recommendations.

Read time: 3 minutes.

HuggingFace assistant

• Overview: HuggingFace is like a hub for AI experts and enthusiasts -like a GitHub for AI. It offers an extensive library of pre-trained models and datasets, making advanced AI accessible to developers, researchers, and businesses around the globe.

• How to use: Choose an AI model that fits your needs, and then interact with it generally like other AI platforms.

• Why we love it ❤️: Easy to use, variety of top open-source models (GPT 3.5, Mistal AI, Meta LLama). A vast community that contributes to making more AI models and assistants and making AI more accessible to people. Transparency - You can view the system instructions of each assistant to learn what makes a good AI assistant and improve upon it for your use.

• Limitations: Open-source models, as of right now, are still not as good as closed-source models, so this may not help you achieve specific tasks. You can read my articles on the ranking of LLMs here.

I tested out one assistant called Website Designer to verify the platform's user experience. It's super easy to use with just a short prompt, and you can view the results here. More importantly, the result is not bad and can be a good developer starting point.

As mentioned, if you like an assistant, you can view the system instructions that make the assistant and create your own improved version. Woohoo!

Check it out here 👉️ link.

LM Studio AI

• Overview: LM studio is a tool to experiment with local and open-source LLMs. You can run these LLMs entirely off your laptop. This approach ensures privacy and that you can control the models completely.

• How to use: Download the software, select the models, and run! Easy peasy. You can view the instructions below.

• Why we love it ❤️: Privacy-focused - The models are run locally and offline. You can use any open-source models on HuggingFace, which means you can try out thousands of AI models with little technical background.

• Limitations:  You might need some technical background to utilize the complete functionalities. You will need hardware to support running the LLM locally, which can be expensive. Here are the hardware requirements.

  1. M1/M2/M3 Mac

  2. Windows PC with a processor that supports AVX2. (Linux is available in beta)

  3. 16GB+ of RAM is recommended

  4. For PCs, 6GB+ of VRAM is recommended

  5. NVIDIA/AMD GPUs supported

Here’s a quick guide on how to use LM Studio:

Step 1: Download the software.

Step 2: Choose a model to download. Once LM Studio has been launched, click on the magnifying glass to skim through the options of models available. Again, take into consideration that these models with be large, therefore it may take a while to download. 

Step 3: Once the model has been downloaded, click the Speech Bubble on the left and select your model for it to load. 

Step 4: Profit! 🚀

Check it out here 👉️ link.

Let me know what other tool you want to be reviewed 🧑‍💻 at [email protected]

That’s a wrap! 🌯

Wrapping it up and stepping into the world of open-source AI tools means you're not just dodging those pesky subscription fees. You're joining a cool, global club that believes in sharing the tech wealth. By checking out the free resources we talked about, you're saving bucks and helping make sure everyone, everywhere, can get in on the AI fun. So, let's keep this party going: explore, share, and give a thumbs up to the open-source vibe. Together, we're turning the tide on the subscription overload and making tech fun and accessible for all. Let's do this!

Thank you for reading ❤️I hope you will find these insights useful. Please contact us at [email protected] if you have suggestions, feedback, or anything!