Instructions to use wlsgusjjn/MedNTDs with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wlsgusjjn/MedNTDs with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="wlsgusjjn/MedNTDs",
	filename="MedNTDs_LoRA.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use wlsgusjjn/MedNTDs 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 wlsgusjjn/MedNTDs:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf wlsgusjjn/MedNTDs:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf wlsgusjjn/MedNTDs:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf wlsgusjjn/MedNTDs: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 wlsgusjjn/MedNTDs:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf wlsgusjjn/MedNTDs: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 wlsgusjjn/MedNTDs:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf wlsgusjjn/MedNTDs:Q4_K_M

Use Docker

docker model run hf.co/wlsgusjjn/MedNTDs:Q4_K_M

LM Studio
Jan
Ollama
How to use wlsgusjjn/MedNTDs with Ollama:
```
ollama run hf.co/wlsgusjjn/MedNTDs:Q4_K_M
```

Unsloth Studio

How to use wlsgusjjn/MedNTDs with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for wlsgusjjn/MedNTDs to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for wlsgusjjn/MedNTDs to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for wlsgusjjn/MedNTDs to start chatting

Atomic Chat new
Docker Model Runner
How to use wlsgusjjn/MedNTDs with Docker Model Runner:
```
docker model run hf.co/wlsgusjjn/MedNTDs:Q4_K_M
```

Lemonade

How to use wlsgusjjn/MedNTDs with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull wlsgusjjn/MedNTDs:Q4_K_M

Run and chat with the model

lemonade run user.MedNTDs-Q4_K_M

List all available models

lemonade list

📦 Model Artifacts

The quantized deployment artifacts for MedNTDs are publicly available.

We provide optimized formats for edge and cross-platform inference:

GGUF (llama.cpp compatible) – for high-performance CPU inference
TFLite (.task) – for mobile and embedded deployment

🔗 Hugging Face Repository

Model files are hosted on Hugging Face:
👉 https://huggingface.co/wlsgusjjn/MedNTDs

🔗 GitHub Repository

Full training pipeline, quantization scripts, and deployment code:
👉 https://github.com/wlsgusjjn/MedNTDs/

These artifacts include:

4-bit quantized GGUF models for offline edge inference
LiteRT / TFLite task models for Flutter-based mobile integration
LoRA-adapted MedGemma checkpoints used in the 2-stage screening pipeline

All models are optimized for low-resource environments and designed for internet-independent deployment in rural clinical settings.

Downloads last month: 1

GGUF

Model size

4B params

Architecture

gemma3

Hardware compatibility

4-bit

View +1 variant

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support