What are the hardware requirements for Phi Med V1?

Phi Med V1 requires approximately 11.1 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Phi Med V1 and how large is it?

Phi Med V1 is developed by justinj92, a model with 2.8b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Phi Med V1?

Phi Med V1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Phi Med V1 by justinj92 — VRAM 11.1GB

Name: Phi Med V1
Author: justinj92

Phi Med V1 is an open-source language model by justinj92. Features: 2.8b LLM, VRAM: 11.1GB, License: apache-2.0, LLM Explorer Score: 0.1.

Custom code Dataset:bi55/medtext En Endpoints compatible Lora Medical Phi-msft Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/justinj92/phi-med-v1

Phi Med V1 Parameters and Internals

Model Type

SLM

Use Cases

Areas:

Testing the effectiveness of Finetuning SLMs

Supported Languages

en (English)

Training Details

Data Sources:

MedText Dataset from HuggingFace

Methodology:

SFT using HF Transformers

Hardware Used:

A10 GPU VMs [2x24GB A10]

Responsible Ai Considerations

Mitigation Strategies:

Model can still hallucinate.

LLM Name	Phi Med V1
Repository 🤗	https://huggingface.co/justinj92/phi-med-v1
Model Size	2.8b
Required VRAM	11.1 GB
Updated	2026-07-20
Maintainer	justinj92
Model Files	0.0 GB 4.9 GB: 1-of-3 4.9 GB: 2-of-3 1.3 GB: 3-of-3 0.0 GB
Supported Languages	en
Model Architecture	AutoModelForCausalLM
License	apache-2.0
Is Biased	none
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	f1\|f2\|Wqkv
LoRA Alpha	16
LoRA Dropout	0.05
R Param	16

Rank the Phi Med V1 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Phi Med V1

Best Alternatives	Context / RAM	Downloads	Likes
Zephyr Rag Agent Webgpt	0K / 40.1 GB	1	1
Phi 2 Electrical Engineering	0K / 5.6 GB	9	27
Phi2 Sqlcoder	0K / 5.6 GB	116	7
Phi2 Bunny	0K / 5.6 GB	66	3

Note: green Score (e.g. "73.2") means that the model is better than justinj92/phi-med-v1.