Arxiv:2407.13833 Arxiv:2505.10717 Arxiv:2507.05517 Arxiv:2507.07248 Autotrain compatible Base model:finetune:microsoft/... Base model:microsoft/phi-3.5-m... Clinical Conversational Dataset:akemih/notechat Dataset:epfl-llm/guidelines Dataset:jpcorb20/medical wikip... Dataset:microsoft/mediflow Dataset:ncbi/pubmed Dataset:starmpcc/asclepius-syn... Dataset:zhengyun21/pmc-patient... En Endpoints compatible Instruct Medical Merge Mergekit Phi3 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/microsoft/MediPhi-Instruct
MediPhi 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)
MediPhi Instruct Parameters and Internals
| LLM Name | MediPhi Instruct |
| Repository 🤗 | https://huggingface.co/microsoft/MediPhi-Instruct |
| Base Model(s) | |
| Model Size | 3.8b |
| Required VRAM | 7.7 GB |
| Updated | 2025-07-20 |
| Maintainer | microsoft |
| Model Type | phi3 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Phi3ForCausalLM |
| License | mit |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.47.0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 32064 |
| Torch Data Type | bfloat16 |
Best Alternatives to MediPhi Instruct
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Phi 4 Mini Instruct | 128K / 7.7 GB | 243538 | 553 |
| Phi 3 Mini 128K Instruct | 128K / 7.7 GB | 525241 | 1655 |
| Phi 3.5 Mini Instruct | 128K / 7.7 GB | 195074 | 891 |
| NuExtract V1.5 | 128K / 7.7 GB | 108511 | 89 |
| Phi 4 Mini Instruct | 128K / 7.7 GB | 4328 | 17 |
| Phi 3.5 Mini TitanFusion 0.1 | 128K / 7.7 GB | 8 | 0 |
| MediPhi Clinical | 128K / 7.7 GB | 204 | 3 |
| NuExtract 1.5 | 128K / 7.7 GB | 5363 | 236 |
| ECE EIFFEL 3Bv2 | 128K / 7.7 GB | 5 | 0 |
| MediPhi PubMed | 128K / 7.7 GB | 72 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than microsoft/MediPhi-Instruct .
Rank the MediPhi 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? 49901 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124