minicpm-v:8b-2.6-q5_K_S

🔥 领先的性能：MiniCPM-V 2.6在最新的OpenCompass版本（对8个流行基准的综合评估）中平均得分达到65.2。凭借仅80亿个参数，它在单图像理解方面超越了广泛使用的专有模型，例如GPT-4o mini、GPT-4V、Gemini 1.5 Pro和Claude 3.5 Sonnet。
🖼️ 多图像理解和上下文学习。MiniCPM-V 2.6还可以对多张图像进行对话和推理。它在流行的多图像基准测试（如Mantis-Eval、BLINK、Mathverse mv和Sciverse mv）上取得了最先进的性能，并在上下文学习能力方面也表现出良好的潜力。
💪 强大的OCR能力：MiniCPM-V 2.6可以处理任何纵横比和最多180万像素的图像（例如，1344x1344）。它在OCRBench上取得了最先进的性能，超越了GPT-4o、GPT-4V和Gemini 1.5 Pro等专有模型。基于最新的RLAIF-V和VisCPM技术，它具有可信赖的行为，在Object HalBench上的幻觉率显著低于GPT-4o和GPT-4V，并支持英语、中文、德语、法语、意大利语、韩语等多种语言。
🚀 卓越的效率：除了其友好的规模外，MiniCPM-V 2.6还在令牌密度（即编码到每个视觉令牌中的像素数量）方面表现出最先进的水平。它在处理180万像素图像时仅产生640个令牌，比大多数模型少75%。这直接提高了推理速度、首个令牌延迟、内存使用率和功耗。

参考文献

GitHub

Hugging Face

> Note: this model requires [Ollama 0.3.10](https://github.com/ollama/ollama/releases/tag/v0.3.10) or later.

MiniCPM-V 2.6 is the latest and most capable model in the MiniCPM-V series. The model is built on SigLip-400M and Qwen2-7B with a total of 8B parameters. It exhibits a significant performance improvement over MiniCPM-Llama3-V 2.5, and introduces new features for multi-image and video understanding. Notable features of MiniCPM-V 2.6 include:

* **🔥 Leading Performance**: MiniCPM-V 2.6 achieves an average score of 65.2 on the latest version of OpenCompass, a comprehensive evaluation over 8 popular benchmarks. With only 8B parameters, it surpasses widely used proprietary models like GPT-4o mini, GPT-4V, Gemini 1.5 Pro, and Claude 3.5 Sonnet for single image understanding.

* **🖼️ Multi Image Understanding and In-context Learning**. MiniCPM-V 2.6 can also perform conversation and reasoning over multiple images. It achieves state-of-the-art performance on popular multi-image benchmarks such as Mantis-Eval, BLINK, Mathverse mv and Sciverse mv, and also shows promising in-context learning capability.

* **💪 Strong OCR Capability**: MiniCPM-V 2.6 can process images with any aspect ratio and up to 1.8 million pixels (e.g., 1344x1344). It achieves state-of-the-art performance on OCRBench, surpassing proprietary models such as GPT-4o, GPT-4V, and Gemini 1.5 Pro. Based on the the latest RLAIF-V and VisCPM techniques, it features trustworthy behaviors, with significantly lower hallucination rates than GPT-4o and GPT-4V on Object HalBench, and supports multilingual capabilities on English, Chinese, German, French, Italian, Korean, etc.

* **🚀 Superior Efficiency**: In addition to its friendly size, MiniCPM-V 2.6 also shows state-of-the-art token density (i.e., number of pixels encoded into each visual token). It produces only 640 tokens when processing a 1.8M pixel image, which is 75% fewer than most models. This directly improves the inference speed, first-token latency, memory usage, and power consumption.

## Refrences

[GitHub](https://github.com/OpenBMB/MiniCPM-V)

[Hugging Face](https://hugging-face.cn/openbmb/MiniCPM-V-2_6)

粘贴、拖放或点击上传图像（.png、.jpeg、.jpg、.svg、.gif）