Arxiv:2405.17220 Arxiv:2408.01800 Any-to-any Asr Audio Custom code Dataset:openbmb/rlaif-v-datase... Feature-extraction Live streaming Minicpm-o Minicpmo Multi-image Multilingual Ocr Omni Realtime speech conversation Region:us Safetensors Sharded Speech Tensorflow Tts Video Vision Voice cloning
Model Card on HF 🤗: https://huggingface.co/openbmb/MiniCPM-o-2_6
MiniCPM O 2 6 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 O 2 6 Parameters and Internals
| LLM Name | MiniCPM O 2 6 |
| Repository 🤗 | https://huggingface.co/openbmb/MiniCPM-o-2_6 |
| Model Size | 8.7b |
| Required VRAM | 17.3 GB |
| Updated | 2025-09-23 |
| Maintainer | openbmb |
| Model Type | minicpmo |
| Model Files | |
| Model Architecture | MiniCPMO |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.44.2 |
| Tokenizer Class | MiniCPMOTokenizerFast |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151700 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Rank the MiniCPM O 2 6 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? 51544 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124