brandonbeiler/InternVL3_5-GPT-OSS-20B-A4B-Preview-FP8-Dynamic Image-Text-to-Text • 21B • Updated Aug 30, 2025 • 6 • 2
Running on Zero Agents Featured 844 Florence 2 📉 844 Generate captions, detections, and segmentations for any image
Running on Zero MCP 57 Multimodal VLM Thinking 🥠 57 Lumian-VLR / VisionThink / MiniCPM-V / Typhoon-OCR / olmOCR
Running on Zero MCP 110 VisionScope-R2 🔍 110 DeepCaption / SkyCaptioner / SpaceThinker / Core / SpaceOm