Qwen Vision Language Models
9 repos
Implementations and variants of Qwen's multimodal vision-language models, including quantized and specialized versions like Vision-R1 (reasoning-focused) and Vision-DeepResearch models. These repositories focus on deploying efficient versions of Qwen3-VL and Qwen3-VL-MoE across different scales and use cases, with emphasis on model serialization via safetensors format for optimized inference.
safetensors ·23
qwen3_vl ·6
qwen3_vl_moe ·2
