Alibaba · Text
Qwen3.5 2B
Alibaba's compact 2B multimodal Qwen model with vision input and a 256K context — fast on-device text+image reasoning.
Modality
Text
Available on
Ollama
Model ID
ollama:qwen3.5:2b
Supported OS
macOSWindowsLinux
Minimum machine configuration
8 GB RAM · 256K ctx · text+image · CPU/GPU
Download size · ~2.7 GB
About the creator
Alibaba
Alibaba's Tongyi research group publishes the Wan video models and the Qwen family of language models.
www.alibabacloud.com ↗Samples
Examples
Sample outputs generated with Qwen3.5 2B will appear here.
Sample coming soon
Sample coming soon
Sample coming soon
More from Alibaba
Wan 2.7
ImageCloud
High-quality diffusion model for detailed, prompt-faithful image generation.
Qwen3.6 27B
TextLocal
Alibaba's 27B multimodal Qwen 3.6 model with a 256K context and strong vision-language reasoning.
Qwen3.6 35B
TextLocal
Alibaba's flagship 35B multimodal Qwen 3.6 model for top-tier vision-language reasoning.
Qwen3.5 4B
TextLocal
Alibaba's efficient 4B multimodal Qwen model with vision input and strong multilingual reasoning.
Qwen3.5 9B
TextLocal
Alibaba's 9B multimodal Qwen model balancing vision-language reasoning with on-device performance.
Qwen3.5 27B
TextLocal
Alibaba's 27B multimodal Qwen model with long-context vision-language reasoning.