MediPhi PubMed is an open-source language model by microsoft. Features: 3.8b LLM, VRAM: 7.7GB, Context: 128K, License: mit, Instruction-Based, LLM Explorer Score: 0.2.
Arxiv:2407.13833 Arxiv:2505.10717 Arxiv:2507.05517 Arxiv:2507.07248 Base model:finetune:microsoft/... Base model:microsoft/phi-3.5-m... Clinical Conversational Dataset:ncbi/pubmed En Endpoints compatible Instruct Medical Merge Mergekit Phi3 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/microsoft/MediPhi-PubMed
MediPhi PubMed 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 PubMed Parameters and Internals
| LLM Name | MediPhi PubMed |
| Repository 🤗 | https://huggingface.co/microsoft/MediPhi-PubMed |
| Base Model(s) | |
| Model Size | 3.8b |
| Required VRAM | 7.7 GB |
| Updated | 2026-04-09 |
| 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 | 4.51.0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 32064 |
| Torch Data Type | bfloat16 |
Best Alternatives to MediPhi PubMed
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Phi 3.5 Mini Instruct | 128K / 7.7 GB | 291298 | 909 |
| Phi 4 Mini Instruct Heretic | 128K / 7.7 GB | 423 | 0 |
| MediPhi Instruct | 128K / 7.7 GB | 3708 | 65 |
| NuExtract V1.5 | 128K / 7.7 GB | 108511 | 89 |
| Phi 3 Mini 128K Instruct | 128K / 7.7 GB | 5 | 0 |
| Phi 3.5 Mini TitanFusion 0.1 | 128K / 7.7 GB | 17 | 0 |
| Phi 4 Mini Instruct | 128K / 7.7 GB | 7198 | 24 |
| ECE EIFFEL 3Bv2 | 128K / 7.7 GB | 9 | 0 |
| MediPhi Clinical | 128K / 7.7 GB | 425 | 14 |
| MediPhi MedCode | 128K / 7.7 GB | 300 | 7 |
Note: green Score (e.g. "73.2") means that the model is better than microsoft/MediPhi-PubMed .
Rank the MediPhi PubMed 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? 53089 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