Instructions to use docvm/medgemma-1.5-4b-it-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use docvm/medgemma-1.5-4b-it-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf docvm/medgemma-1.5-4b-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf docvm/medgemma-1.5-4b-it-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf docvm/medgemma-1.5-4b-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf docvm/medgemma-1.5-4b-it-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf docvm/medgemma-1.5-4b-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf docvm/medgemma-1.5-4b-it-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf docvm/medgemma-1.5-4b-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf docvm/medgemma-1.5-4b-it-GGUF:Q4_K_M

Use Docker

docker model run hf.co/docvm/medgemma-1.5-4b-it-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use docvm/medgemma-1.5-4b-it-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "docvm/medgemma-1.5-4b-it-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "docvm/medgemma-1.5-4b-it-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/docvm/medgemma-1.5-4b-it-GGUF:Q4_K_M

Ollama
How to use docvm/medgemma-1.5-4b-it-GGUF with Ollama:
```
ollama run hf.co/docvm/medgemma-1.5-4b-it-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use docvm/medgemma-1.5-4b-it-GGUF with Docker Model Runner:
```
docker model run hf.co/docvm/medgemma-1.5-4b-it-GGUF:Q4_K_M
```

Lemonade

How to use docvm/medgemma-1.5-4b-it-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull docvm/medgemma-1.5-4b-it-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.medgemma-1.5-4b-it-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

MedGemma 1.5 4B IT — GGUF Quantized

GGUF quantization of google/medgemma-1.5-4b-it for mobile/edge deployment.

File

File	Quant	Size	Use case
`medgemma-1.5-4b-it-Q4_K_M.gguf`	Q4_K_M	~2.5 GB	Mobile / edge devices

Usage

With llama.cpp

llama-cli -m medgemma-1.5-4b-it-Q4_K_M.gguf -cnv

With Ollama

Create a Modelfile:

FROM ./medgemma-1.5-4b-it-Q4_K_M.gguf

Then:

ollama create medgemma -f Modelfile
ollama run medgemma

On Android (llama.cpp Android build / MLC LLM)

Use the Q4_K_M file (~2.5 GB fits in most modern phone RAM).

Intended Use — Sakhi

This model powers Sakhi, an AI clinical companion for ASHA workers in rural India, with 3 modes:

CHECKUP — ANC readings → risk assessment
NEWBORN — Home visit findings → risk assessment
CHAT — Free-form clinical Q&A

Safety

NOT a medical device or diagnostic tool
Requires clinical oversight
When in doubt, always refer to PHC

License

Health AI Developer Foundations Terms of Use

Downloads last month: 81

GGUF

Model size

4B params

Architecture

gemma3

Hardware compatibility

4-bit

Model tree for docvm/medgemma-1.5-4b-it-GGUF

Base model

google/medgemma-1.5-4b-it

Quantized

(42)

this model