What are the hardware requirements for MiniCPM5 Vision 2B?

MiniCPM5 Vision 2B requires approximately 5.9 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed MiniCPM5 Vision 2B and how large is it?

MiniCPM5 Vision 2B is developed by ewin-reg, a model with 2b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate MiniCPM5 Vision 2B?

MiniCPM5 Vision 2B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

MiniCPM5 Vision 2B by ewin-reg — VRAM 5.9GB

Name: MiniCPM5 Vision 2B
Author: ewin-reg

MiniCPM5 Vision 2B is an open-source language model by ewin-reg. Features: 2b LLM, VRAM: 5.9GB, License: apache-2.0, LLM Explorer Score: 0.31.

Arxiv:2303.15343 Arxiv:2404.06395 Custom code Document-parsing En Endpoints compatible Image-text-to-text Minicpm5 Minicpm5 v Multimodal Ocr Region:us Safetensors Table-extraction Vision Visual-grounding Zh

Model Card on HF 🤗: https://huggingface.co/ewin-reg/MiniCPM5-Vision-2B

MiniCPM5 Vision 2B Parameters and Internals

LLM Name	MiniCPM5 Vision 2B
Repository 🤗	https://huggingface.co/ewin-reg/MiniCPM5-Vision-2B
Model Size	2b
Required VRAM	5.9 GB
Updated	2026-09-12
Maintainer	ewin-reg
Model Type	minicpm5_v
Model Files	5.9 GB
Supported Languages	en zh
Model Architecture	AutoModel
License	apache-2.0

Rank the MiniCPM5 Vision 2B capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to MiniCPM5 Vision 2B

Best Alternatives	Context / RAM	Downloads	Likes
Nemotron Labs Audex 2B	0K / GB	2466	86
...B Vlm Weld Explainability Lora	0K / 0 GB	65	1
Genx Synthetic Data Generator	0K / 0 GB	15	0
Food Analysis	0K / 0.1 GB	0	6
Gemma2 2B Code Lora	0K / 0.1 GB	0	1
Sql Gemma 2M	0K / GB	1	1
...emma 2B Finetuned Sft Navarasa	0K / 0.3 GB	0	7
Telugu Gemma 2B Finetuned Sft	0K / 0.3 GB	0	3
...arge.clip Laion2b Soup Ft In1k	0K / 3.4 GB	12376	5
Ct2fast Codegen 2B Mono	0K / 5.6 GB	6	1

Note: green Score (e.g. "73.2") means that the model is better than ewin-reg/MiniCPM5-Vision-2B.