Qwen3.5 Small
0.8B-9B native multimodal w/ more intelligence, less compute
Visit website →About
The Qwen3.5 Small series is a set of four models from Qwen, at 0.8B, 2B, 4B, and 9B parameters. They are natively multimodal, with an improved architecture and scaled reinforcement learning.
The 0.8B and 2B models are small and fast for edge devices, the 4B model works as a strong lightweight base for agents, and the 9B model closes much of the gap with far larger models. Base versions are also released.
It is aimed at developers who need capable open models that run efficiently, on phones, edge hardware, or modest servers, and want a range of sizes to match the compute they have available.
AI-assisted draft, human-reviewed before publishing — see how we choose & review tools.
Why we picked it
Qwen3.5 Small made the list for the size spread within one family — a 0.8B model for an edge device and a 9B model closing the gap with far larger ones means picking a size for your actual hardware instead of one model that assumes a server.
Related tools
- 1 Microsoft Copilot Microsoft's AI assistant, free to chat and bundled into Microsoft 365 Freemium
- 2 Chat.sh AI help center that answers directly instead of listing titles Freemium
- 3 Yedric.ai Let SaaS users control your product with natural language Free
- 4 Gemini Google's assistant, deepest inside Gmail, Docs, Drive and Android Freemium
- 5 Claude Anthropic's assistant, strongest on long documents and Gulf-dialect nuance Freemium
- 6 ChatGPT The general-purpose AI assistant most people mean when they say "AI" Freemium