DeepSeek has just released a powerful new 8B model 🔥 This means you can run it locally and for free on a laptop with zero limitations. You just need LM Studio and 4Gb of RAM. The few quick steps below:

1. Download LM Studio (free) Go to and download the version for your OS. Available for: - Windows (x86/ARM) - macOS (M series) - Linux

2. Download the model In LM Studio, in the search tab, type: “deepseek r1 0528 qwen 8b” I suggest the bartowski version with the "Q4_0" quantization, suitable for most devices. (If you're using macOS, opt for an MLX model). Then, just click on download.

3. Load and chat Once the model is downloaded 1. Create a new chat 2. Select the model you've just downloaded 3. Add a system prompt to avoid overthinking That's it! You're ready to use DeepSeek R1 0528 Qwen 8B fully offline and locally!

Only 4GB haha And LMStudio is really perfect for open source

The size/performance ratio is just mind-blowing. SLMs are evolving very quickly.

Here I share an XGBoost model that delivers a 25% CAGR with minimal drawdown on Visa stock. In this free Substack post I share code and commentary for a powerful Machine Learning strategy that delivers powerful returns.

This is a huge step forward for accessible local LLMs. Running an 8B model like DeepSeek R1-0528 on just 4GB RAM is no joke it really shows how far quantization and optimization have come. LM Studio makes the whole process seamless too.

That's a great AI summary actually haha

4GB Memory not same as 4GB GPU... "on a laptop" is a big generalization.

Yeah you're right. Let's say it works with 4GB of unified RAM, which is what most modern laptops have. But I should have been a little more specific.

Open-source is winning again 🔥

And it's almost too much winning 😂