Qwen
The smartest model one gaming graphics card runs. Sizes 0.8B to 2.4T.
Best overallFreeOpenRuns on your PC
- Best for
- Writing, coding, documents, image questions
- On your PC
- Some setup
- Works on
- Windows, Mac, Linux
- License
- Apache-2.0
What’s good
- Top quality among models that fit one home computer
- Reads images and video, very long documents
- Apache-2.0 license, free for commercial use
Downsides
- 27B needs a 24 GB graphics card or 32 GB Mac
- On smaller machines use Qwen3.5 9B (7 GB download) instead
- Thinks before answering, so replies can feel slow
At a glance.
- Best for
- Writing, coding, documents, image questions
- Price
- Free, open source
- Version
- Qwen3.8 27BReleased 2026-08
- Works on
- Windows, Mac, Linux
- Open source
- Yes, Apache-2.0
- Made by
- Alibaba (Qwen team)
- Website
- qwen.ai
How it ranks.
- LMArena Text#106 · 14362026-10-27
- Artificial Analysis Progress Index, small open models#2 · 3032026-11-05
Can I run it myself?
Yes. Some setup: download a model inside an app.
Use LM Studio, Ollama, Jan, llama.cpp.
- You need
- 24 GB graphics card or Mac with 32 GB memory
- Setup
- Some setupDownload a model inside an app
- Laptop, 8 GBToo small
- PC, 16 GB+Too small
- Mac, 16 GBToo small
- Mac, 32 GBRuns
- Mac, 64 GB+Runs
- PC, 8 GB GPUToo small
- PC, 12 GB GPUToo small
- PC, 16 GB GPUToo small
- PC, 24 GB GPURuns
- WorkstationRuns