Instructions to use SandLogicTechnologies/MedScholar-1.5B-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 SandLogicTechnologies/MedScholar-1.5B-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 SandLogicTechnologies/MedScholar-1.5B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf SandLogicTechnologies/MedScholar-1.5B-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 SandLogicTechnologies/MedScholar-1.5B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf SandLogicTechnologies/MedScholar-1.5B-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 SandLogicTechnologies/MedScholar-1.5B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf SandLogicTechnologies/MedScholar-1.5B-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 SandLogicTechnologies/MedScholar-1.5B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SandLogicTechnologies/MedScholar-1.5B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/SandLogicTechnologies/MedScholar-1.5B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use SandLogicTechnologies/MedScholar-1.5B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SandLogicTechnologies/MedScholar-1.5B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SandLogicTechnologies/MedScholar-1.5B-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/SandLogicTechnologies/MedScholar-1.5B-GGUF:Q4_K_M

Ollama
How to use SandLogicTechnologies/MedScholar-1.5B-GGUF with Ollama:
```
ollama run hf.co/SandLogicTechnologies/MedScholar-1.5B-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use SandLogicTechnologies/MedScholar-1.5B-GGUF with Docker Model Runner:
```
docker model run hf.co/SandLogicTechnologies/MedScholar-1.5B-GGUF:Q4_K_M
```

Lemonade

How to use SandLogicTechnologies/MedScholar-1.5B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SandLogicTechnologies/MedScholar-1.5B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.MedScholar-1.5B-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

Quantized MedScholar-1.5B

This repository provides quantized GGUF versions of the yasserrmd/MedScholar-1.5B. These 4-bit and 5-bit quantized variants retain the original model’s strengths in multimodal medical reasoning, while reducing memory and compute requirements—ideal for efficient inference on resource-constrained devices.

Model Overview

Original Model: yasserrmd/MedScholar-1.5B
Quantized Versions:
- Q4_K_M (4-bit quantization)
- Q5_K_M (5-bit quantization)
Architecture: Decoder-only transformer
Base Model: Qwen2.5-1.5B-Instruct-unsloth-bnb-4bit
Training Framework: Unsloth + QLoRA
Dataset: MIRIAD-4.4M (1M samples) [ODC-By 1.0]
License: Apache-2.0 (inherits from base model); dataset is ODC-By 1.0
Language: English

Quantization Details

Q4_K_M Version

Approx. ~68% size reduction
Lower memory footprint (~940 MB)
Best suited for deployment on edge devices or low-resource GPUs
Slight performance degradation in complex reasoning scenarios

Q5_K_M Version

Approx. ~64% size reduction
Higher fidelity (~1.04 GB)
Better performance retention, recommended when quality is a priority

Usage

Below, there are some code snippets on how to get quickly started with running the model. llama.cpp (text-only)

./llama-cli -hf SandLogicTechnologies/MedScholar-1.5B-GGUF -p "What are the symptoms of diabetes"

Note

⚠️ This model is for research, educational, and exploration purposes only. It is not a medical device and must not be used to provide clinical advice, diagnosis, or treatment.

Acknowledgments

These quantized models are based on the original work by the [https://huggingface.co/yasserrmd/MedScholar-1.5B].
MIRIAD Dataset by Zheng et al. (2025) – [https://huggingface.co/datasets/miriad/miriad-4.4M].
Qwen2.5 by Alibaba - [https://huggingface.co/Qwen].
Training infrastructure: [https://github.com/unslothai/unsloth].

Contact

For any inquiries or support, please contact us at support@sandlogic.com or visit our Website.

Downloads last month: 31

GGUF

Model size

2B params

Architecture

qwen2

Hardware compatibility

4-bit

5-bit

Model tree for SandLogicTechnologies/MedScholar-1.5B-GGUF

Base model

yasserrmd/MedScholar-1.5B

Quantized

(5)

this model