Get started with Qwen
Compare Qwen model files, check what is hosted here, and find setup steps or an online demo when available.
Choose a size
Compare file sizes with your computer’s memory. The model page shows the full setup requirements.
Suggested starting point
AtomicChat/Qwen3-4B-DFlash-GGUF · 0.577 GB · mit
Model Size Hosted Next step 0bserverx/Qwen3.8-27B-Heretic-GSQ-RCO-GGUF 81.09 GB (repository total) Yes (10 files) Alittlehammmer/Qwen3.6-27B-DFlash-GGUF-llama.cpp 1.03 GB Yes (1 file) Alittlehammmer/Qwen3.6-35B-A3B-DFlash-GGUF-llama.cpp 2.05 GB (repository total) Yes (1 file) AnkitAI/Parable-Qwen3-4B-Claude-Fable-5-GGUF 2.50 GB Yes (1 file) AnkitAI/Parable-Qwen3-8B-Claude-Fable-5-GGUF 5.03 GB Yes (1 file) AtomicChat/Qwen3-4B-DFlash-GGUF 0.577 GB Yes (1 file) AtomicChat/Qwen3.5-4B-DFlash-GGUF 0.685 GB Yes (1 file) axolotl-ai-co/tiny-qwen3-129m 0.270 GB (repository total) Yes (6 files) Download a verified copy
Open the model page to check whether its files are hosted here and have a checksum.
Run the model
Follow the setup steps on the model page. If an online demo is available, you can try Bay Run there.
File sizes and links reflect the catalog at render time. They are not a runtime guarantee.