Older but still usable Qwen models:

• qwen:0.5b
• qwen:1.8b
• qwen:4b
• qwen:7b
• qwen:14b
• qwen:32b
• qwen:72b
• qwen:110b

Good baseline multilingual models with broad general-purpose use.

Qwen 2.5 is popular for local use and improved reasoning.

ollama run qwen2.5:7b

Good local sweet spots include:

• qwen2.5:7b
• qwen2.5:14b
• qwen2.5:32b
• qwen2.5:72b

Optimized for programming, debugging, and code generation.

• qwen2.5-coder:0.5b
• qwen2.5-coder:1.5b
• qwen2.5-coder:3b
• qwen2.5-coder:7b
• qwen2.5-coder:14b
• qwen2.5-coder:32b

ollama run qwen2.5-coder:14b

Newer generation with improved reasoning and agent-like behavior.

• qwen3:0.6b
• qwen3:1.7b
• qwen3:4b
• qwen3:8b
• qwen3:14b
• qwen3:30b
• qwen3:32b
• qwen3:235b

ollama run qwen3:8b

More refined mainstream generation with stronger reasoning and model options.

• qwen3.5:0.8b
• qwen3.5:2b
• qwen3.5:4b
• qwen3.5:9b
• qwen3.5:27b
• qwen3.5:35b
• qwen3.5:122b

ollama run qwen3.5:27b

Vision-capable models for text and image understanding.

• qwen3-vl:2b
• qwen3-vl:4b
• qwen3-vl:8b
• qwen3-vl:30b
• qwen3-vl:32b
• qwen3-vl:235b

ollama run qwen3-vl:8b

• Lightweight laptop: qwen2.5:7b or qwen3:4b
• Best coding: qwen2.5-coder:14b or qwen2.5-coder:32b
• Best reasoning: qwen3.5:27b or qwen3.5:35b
• Images: qwen3-vl:8b

ollama run qwen2.5:7b
ollama run qwen2.5-coder:14b
ollama run qwen3:8b
ollama run qwen3.5:27b
ollama run qwen3-vl:8b