Qwen3.5 9B

Qwen3.5 9B is a multimodal foundation model from the Qwen 3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design with early fusion of multimodal tokens, supporting text, image, and video inputs while producing text outputs with built-in reasoning capabilities.

Qwen: Qwen3.5 35B A3B

The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall performance is comparable to that of the Qwen3.5-27B.

Qwen: Qwen3.5 122B A10B

The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of overall performance, this model is second only to Qwen3.5-397B-A17B. Its text capabilities significantly outperform those of Qwen3-235B-2507, and its visual capabilities surpass those of Qwen3-VL-235B.

Qwen: Qwen3.5 Flash

The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the 3 series, these models deliver a leap forward in performance for both pure text and multimodal tasks, offering fast response times while balancing inference speed and overall performance.

Qwen: Qwen3.5 Plus 2026-02-15

The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of task evaluations, the 3.5 series consistently demonstrates performance on par with state-of-the-art leading models. Compared to the 3 series, these models show a leap forward in both pure-text and multimodal capabilities. Supports text, image, and video inputs with reasoning and tool use.

Qwen: Qwen3.5 397B A17B

The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers state-of-the-art performance comparable to leading-edge models across a wide range of tasks, including language understanding, logical reasoning, code generation, agent-based tasks, image understanding, video understanding, and GUI interactions. With its robust code-generation and agent capabilities, the model exhibits strong generalization across diverse agent scenarios. Supports 201 languages and dialects.

Qwen3.5 9B

Qwen3.5 9B is a multimodal foundation model from the Qwen 3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design with early fusion of multimodal tokens, supporting text, image, and video inputs while producing text outputs with built-in reasoning capabilities.

Qwen: Qwen3.5 35B A3B

The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall performance is comparable to that of the Qwen3.5-27B.

Qwen: Qwen3.5 122B A10B

The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of overall performance, this model is second only to Qwen3.5-397B-A17B. Its text capabilities significantly outperform those of Qwen3-235B-2507, and its visual capabilities surpass those of Qwen3-VL-235B.

Qwen: Qwen3.5 Flash

The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the 3 series, these models deliver a leap forward in performance for both pure text and multimodal tasks, offering fast response times while balancing inference speed and overall performance.

Qwen: Qwen3.5 Plus 2026-02-15

The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of task evaluations, the 3.5 series consistently demonstrates performance on par with state-of-the-art leading models. Compared to the 3 series, these models show a leap forward in both pure-text and multimodal capabilities. Supports text, image, and video inputs with reasoning and tool use.

Qwen: Qwen3.5 397B A17B

The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers state-of-the-art performance comparable to leading-edge models across a wide range of tasks, including language understanding, logical reasoning, code generation, agent-based tasks, image understanding, video understanding, and GUI interactions. With its robust code-generation and agent capabilities, the model exhibits strong generalization across diverse agent scenarios. Supports 201 languages and dialects.