model

Qwen2.5-VL-32B-Instruct

modelactiveqwen2-5-vl-32b-instruct-4bf34a37·1 events·first seen 1mo ago

Aliases: Qwen2.5-VL-32B-Instruct

Co-occurring entities

Qwen2.5-VL Apache 2.0 Hugging Face Reinforcement Learning Alibaba Qwen Team

More like this (12)

Qwen2.5-Coder-32B-Instruct Qwen2.5-7B-Instruct-1M Qwen3-30B-A3B-Instruct Qwen2.5-VL Qwen3-Coder-480B-A35B-Instruct Qwen-2.5-VL-3B Qwen3-4B-Instruct Qwen2-Audio-7B-Instruct Qwen 2.5 32B Instruct Qwen1.5-32B Qwen-3-VL-2B Qwen2-57B-A14B

Recent events (1)

7Qwen Research·1mo ago·source ↗

Qwen2.5-VL-32B: Reinforcement-Learning-Optimized Vision-Language Model Released

Alibaba's Qwen team has released Qwen2.5-VL-32B-Instruct, a 32-billion-parameter vision-language model built on the Qwen2.5-VL series and further optimized with reinforcement learning. The model is open-sourced under the Apache 2.0 license and available on Hugging Face and ModelScope. It follows the January 2025 launch of the broader Qwen2.5-VL series, positioning the 32B scale as a balance between capability and deployment practicality.

Open Weights Progress Inference Economics Qwen2.5-VL Qwen2.5-VL-32B-Instruct Apache 2.0 +5 more