The most powerful vision-language model in the Qwen model family to date.
1.3M Pulls 59 Tags Updated 3 months ago
The most powerful vision-language model in the Qwen3 model family to date.
43K Pulls 54 Tags Updated 2 months ago
11 Pulls 1 Tag Updated 2 weeks ago
76 Pulls 1 Tag Updated 3 months ago
68 Pulls 1 Tag Updated 3 months ago
37 Pulls 1 Tag Updated 3 months ago
The version of the large-scale quantitative model obtained by imitating the previous experts
26 Pulls 1 Tag Updated 1 month ago
15 Pulls 1 Tag Updated 3 months ago
13 Pulls 1 Tag Updated 3 months ago
11 Pulls 1 Tag Updated 3 months ago
8 Pulls 1 Tag Updated 3 months ago
5 Pulls 1 Tag Updated 1 month ago
5 Pulls 1 Tag Updated 3 months ago
4 Pulls 1 Tag Updated 3 months ago
Optimized 8B (qwen3-vl:8b) for OpenClaw agents. Precise JSON tool calls, <thinking> reasoning, temp 0.5, 16k ctx. Runs smoothly on 8GB VRAM laptops with minimal hallucinations.
1 Tag Updated 4 minutes ago
664 Pulls 1 Tag Updated 1 month ago
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.
495 Pulls 1 Tag Updated 1 month ago
449 Pulls 2 Tags Updated 1 month ago
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.
187 Pulls 3 Tags Updated 1 month ago