Modelmultimodalv2.6

MiniCPM-V 2.6

by Tsinghua University (ModelBest) · free · Last verified 2026-03-17

MiniCPM-V 2.6 is a compact yet capable vision-language model from Tsinghua University, designed for deployment on edge devices and mobile platforms while achieving GPT-4V-level performance on several visual benchmarks. It supports high-resolution images and multi-image inputs, making it remarkably capable relative to its small footprint.

https://huggingface.co/openbmb/MiniCPM-V-2_6 ↗

C+

C+—Average

Adoption: C+Quality: AFreshness: ACitations: C+Engagement: F

Specifications

License: Apache 2.0
Pricing: free
Capabilities: vision, visual-question-answering, ocr, image-captioning, multi-image-understanding
Integrations: Hugging Face, Ollama, LM Studio
Use Cases: edge-deployment, mobile-ai, visual-qa, document-analysis, on-device-vision
API Available: Yes
Parameters: 8B
Context Window: 128K
Modalities: text, image
Training Cutoff: 2024
Tags: tsinghua, efficient, vision-language, open-source, edge-deployment
Added: 2026-03-17
Completeness: 100%

Index Score

53.6

Adoption

Quality

Freshness

Citations

Engagement

Explore the full AI ecosystem on Agents as a Service