Arxiv:2407.13833 Ar Audio Automatic-speech-recognition Autotrain compatible Code Cs Custom code Da De En Es Fi Fr He Hu Instruct It Ja Ko Multilingual Nl No Phi Phi-4-mini Phi-4-multimodal Phi4mm Pl Pt Region:us Ru Safetensors Sharded Speech-summarization Speech-translation Sv Tensorflow Th Tr Uk Visual-question-answering Zh
Model Card on HF 🤗: https://huggingface.co/microsoft/Phi-4-multimodal-instruct
Phi 4 Multimodal Instruct 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)
Phi 4 Multimodal Instruct Parameters and Internals
| LLM Name | Phi 4 Multimodal Instruct |
| Repository 🤗 | https://huggingface.co/microsoft/Phi-4-multimodal-instruct |
| Model Size | 5.6b |
| Required VRAM | 11.2 GB |
| Updated | 2025-03-15 |
| Maintainer | microsoft |
| Model Type | phi4mm |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | ar zh cs da nl en fi fr de he hu it ja ko pl pt ru es sv th tr uk |
| Model Architecture | Phi4MMForCausalLM |
| License | mit |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.46.1 |
| Tokenizer Class | GPT2TokenizerFast |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 200064 |
| Torch Data Type | bfloat16 |
Rank the Phi 4 Multimodal Instruct 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? 45097 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227