← all releases
Alibaba Cloud·Apr 29, 2025·v3.5·open source
Qwen3.5
Qwen3.5 is the latest series in the Qwen family of large language models developed by Alibaba Cloud's Qwen team. It offers advanced capabilities in natural language understanding and generation, building upon previous iterations to provide enhanced performance and versatility.
AI AgentsAgentic AILLMsML
overview
Qwen3.5 is the latest series in the Qwen family of large language models developed by Alibaba Cloud's Qwen team. It offers advanced capabilities in natural language understanding and generation, building upon previous iterations to provide enhanced performance and versatility.
key features
- 01Dense and Mixture-of-Experts (MoE) models of various sizes, including 0.6B, 1.7B, 4B, 8B, 14B, 32B, and 30B-A3B, 235B-A22B.
- 02Seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose chat).
- 03Significant enhancements in reasoning capabilities, surpassing previous models in mathematics, code generation, and commonsense logical reasoning.
- 04Superior human preference alignment, excelling in creative writing, role-playing, multi-turn dialogues, and instruction following.
- 05Expertise in agent capabilities, enabling precise integration with external tools in both thinking and non-thinking modes.
related productsbrowse all →
AIBuildAIopen sourceAIBuildAI is an AI agent that autonomously constructs AI models. Given a specific task, it initiates an agent loop to analyze the problem, design models, and execute training processes, all without human intervention.llmockopen sourcellmock is a deterministic mock LLM server designed for testing purposes. It provides a real HTTP server with authentic SSE streams, allowing developers to simulate interactions with various LLM APIs like OpenAI, Claude, and Gemini without incurring costs or dealing with non-deterministic results.MiroThinkeropen sourceMiroThinker is an open-source search agent model developed by MiroMindAI, designed for tool-augmented reasoning and real-world information seeking. It aims to match the deep research capabilities of leading AI models like OpenAI's Deep Research and Google's Gemini Deep Research.