DeepSeek R1 (distilled)
The famous thinking model, shrunk to 8B so laptops can run it.
FreeOpen sourceRuns on your PC
- Best for
- A thinking model on laptops
- On your PC
- Some setup
- Works on
- Windows, Mac, Linux
- License
- MIT
What’s good
- Runs on most laptops with 8 GB memory
- Shows its step by step thinking
- Well known, in every local AI app
Downsides
- Old (May 2025); Gemma 4 and Qwen3.5 now beat it
- Real DeepSeek V4 models are far too big for home
- Long thinking makes simple answers slow
At a glance.
- Best for
- A thinking model on laptops
- Price
- Free, open source
- Version
- DeepSeek-R1-0528-Qwen3-8BReleased 2025-05
- Works on
- Windows, Mac, Linux
- Open source
- Yes, MIT
- Made by
- DeepSeek
- Website
- deepseek.com
Should you use it?
It is #8 of 10. Good for a thinking model on laptops; for most people, Qwen is the better start.
Can I run it myself?
Yes. Some setup: download a model inside an app.
Use LM Studio, Ollama, Jan, llama.cpp.
- You need
- Any laptop with 8 GB RAM; faster with a graphics card
- Setup
- Some setupDownload a model inside an app
- Laptop, 8 GBRuns
- PC, 16 GB+Runs
- Mac, 16 GBRuns
- Mac, 32 GBRuns
- Mac, 64 GB+Runs
- PC, 8 GB GPURuns
- PC, 12 GB GPURuns
- PC, 16 GB GPURuns
- PC, 24 GB GPURuns
- WorkstationRuns