Flagship vision-language model of Qwen and also a significant leap from the previous Qwen2-VL.
The most powerful vision-language model in the Qwen model family to date.
MiniCPM-V surpasses proprietary models such as GPT-4V, Gemini Pro, Qwen-VL and Claude 3 in overall performance, and support multimodal conversation for over 30 languages.
pulled as BF16, vocab slice (combined_en_huge) requant to IQ4_NL (combined_en_huge) -- (English + Coding focus) - ~20% faster than Q4_K_M
🚀 State-of-the-Art Qwen3-VL GUI & Mobile Agent (Q8_0) with intact CLIP vision projector for high-precision UI grounding, OCR, and automation.
full BF16 model, hand-requant to IQ4_NL, with combined_en_huge dataset (English + Coding focus)
The Qwen3-VL-Reranker model series are the latest additions to the Qwen family, built upon the recently open-sourced and powerful Qwen3-VL foundation model.
The Qwen3-VL-Embedding model series are the latest additions to the Qwen family, built upon the recently open-sourced and powerful Qwen3-VL foundation model.
German-OCR-Turbo ist ein fine-tuned Vision-Language-Modell basierend auf Qwen3-VL-2B, optimiert für die präzise Texterkennung aus deutschen Rechnungen, Formularen und Geschäftsdokumenten. Das Modell extrahiert strukturierte Daten im Markdown-Format.
Qwen 3 VL but like Heretic.
Alibaba Tongyi GUI agent on Qwen3-VL. SOTA: 73.5% ScreenSpot-Pro, 76.7% AndroidWorld. Returns bbox [x1,y1,x2,y2] for UI automation. Supports MCP tools & device-cloud collaboration. Apache 2.0. Tags: 2b (default), 8b.