MiniCPM Llama3 V 2 5 is an open-source language model by openbmb. Features: 8.5b LLM, VRAM: 17GB, Context: 8K, LLM Explorer Score: 0.23.
Conversational Custom code Dataset:openbmb/rlaif-v-datase... Feature-extraction Image-text-to-text Minicpm-v Minicpmv Multilingual Ocr Region:us Safetensors Sharded Tensorflow Vision
Model Card on HF 🤗: https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5
MiniCPM Llama3 V 2 5 Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
MiniCPM Llama3 V 2 5 Parameters and Internals
| LLM Name | MiniCPM Llama3 V 2 5 |
| Repository 🤗 | https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5 |
| Model Size | 8.5b |
| Required VRAM | 17 GB |
| Updated | 2026-05-14 |
| Maintainer | openbmb |
| Model Type | minicpmv |
| Model Files | |
| Model Architecture | MiniCPMV |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.40.0 |
| Tokenizer Class | MiniCPMVTokenizerFast |
| Padding Token | ! |
| Vocabulary Size | 128256 |
| Torch Data Type | float16 |
Rank the MiniCPM Llama3 V 2 5 Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 53727 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a