Instructions to use prithivMLmods/OpenMed-SynthVision-MedVL-AIO-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/OpenMed-SynthVision-MedVL-AIO-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("visual-question-answering", model="prithivMLmods/OpenMed-SynthVision-MedVL-AIO-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("prithivMLmods/OpenMed-SynthVision-MedVL-AIO-GGUF", device_map="auto")

llama-cpp-python

How to use prithivMLmods/OpenMed-SynthVision-MedVL-AIO-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="prithivMLmods/OpenMed-SynthVision-MedVL-AIO-GGUF",
	filename="Ministral-3B-MedVL-GGUF/Ministral-3B-MedVL.BF16.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 prithivMLmods/OpenMed-SynthVision-MedVL-AIO-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 prithivMLmods/OpenMed-SynthVision-MedVL-AIO-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/OpenMed-SynthVision-MedVL-AIO-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf prithivMLmods/OpenMed-SynthVision-MedVL-AIO-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/OpenMed-SynthVision-MedVL-AIO-GGUF:BF16

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 prithivMLmods/OpenMed-SynthVision-MedVL-AIO-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf prithivMLmods/OpenMed-SynthVision-MedVL-AIO-GGUF:BF16

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 prithivMLmods/OpenMed-SynthVision-MedVL-AIO-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf prithivMLmods/OpenMed-SynthVision-MedVL-AIO-GGUF:BF16

Use Docker

docker model run hf.co/prithivMLmods/OpenMed-SynthVision-MedVL-AIO-GGUF:BF16

LM Studio
Jan
Ollama
How to use prithivMLmods/OpenMed-SynthVision-MedVL-AIO-GGUF with Ollama:
```
ollama run hf.co/prithivMLmods/OpenMed-SynthVision-MedVL-AIO-GGUF:BF16
```

Unsloth Studio

How to use prithivMLmods/OpenMed-SynthVision-MedVL-AIO-GGUF 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 prithivMLmods/OpenMed-SynthVision-MedVL-AIO-GGUF 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 prithivMLmods/OpenMed-SynthVision-MedVL-AIO-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for prithivMLmods/OpenMed-SynthVision-MedVL-AIO-GGUF to start chatting

How to use prithivMLmods/OpenMed-SynthVision-MedVL-AIO-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prithivMLmods/OpenMed-SynthVision-MedVL-AIO-GGUF:BF16

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "prithivMLmods/OpenMed-SynthVision-MedVL-AIO-GGUF:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use prithivMLmods/OpenMed-SynthVision-MedVL-AIO-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prithivMLmods/OpenMed-SynthVision-MedVL-AIO-GGUF:BF16

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default prithivMLmods/OpenMed-SynthVision-MedVL-AIO-GGUF:BF16

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use prithivMLmods/OpenMed-SynthVision-MedVL-AIO-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prithivMLmods/OpenMed-SynthVision-MedVL-AIO-GGUF:BF16

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "prithivMLmods/OpenMed-SynthVision-MedVL-AIO-GGUF:BF16" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use prithivMLmods/OpenMed-SynthVision-MedVL-AIO-GGUF with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/OpenMed-SynthVision-MedVL-AIO-GGUF:BF16
```

Lemonade

How to use prithivMLmods/OpenMed-SynthVision-MedVL-AIO-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prithivMLmods/OpenMed-SynthVision-MedVL-AIO-GGUF:BF16

Run and chat with the model

lemonade run user.OpenMed-SynthVision-MedVL-AIO-GGUF-BF16

List all available models

lemonade list

OpenMed-SynthVision-MedVL-AIO-GGUF

OpenMed's MedVL series—comprising Qwen2.5-3B-MedVL, Qwen3.5-2B-MedVL, and Ministral-3B-MedVL—are lightweight, specialized medical vision-language models fine-tuned from their respective strong open-source bases (Qwen2.5-VL-3B, Qwen3.5-2B, Ministral-3B) for clinical applications like radiology report generation, medical VQA, pathology slide analysis, dermatology lesion identification, and multimodal diagnostics across X-rays, CT/MRI scans, histopathology images, and ophthalmic fundus photos. These ~2-3B parameter models prioritize edge deployment on laptops/single GPUs via efficient architectures (Qwen's dynamic resolution ViT + Gated DeltaNet, Ministral's optimized SLM design), achieving high-fidelity medical reasoning, anatomical localization, disease classification, and report structuring while preserving layout/spatial awareness for real-world hospital workflows.

Model Files

Qwen2.5-3B-MedVL

File Name	Quant Type	File Size	File Link
Qwen2.5-3B-MedVL.BF16.gguf	BF16	6.18 GB	Download
Qwen2.5-3B-MedVL.F16.gguf	F16	6.18 GB	Download
Qwen2.5-3B-MedVL.F32.gguf	F32	12.3 GB	Download
Qwen2.5-3B-MedVL.Q8_0.gguf	Q8_0	3.29 GB	Download
Qwen2.5-3B-MedVL.mmproj-bf16.gguf	mmproj-bf16	1.34 GB	Download
Qwen2.5-3B-MedVL.mmproj-f16.gguf	mmproj-f16	1.34 GB	Download
Qwen2.5-3B-MedVL.mmproj-f32.gguf	mmproj-f32	2.67 GB	Download
Qwen2.5-3B-MedVL.mmproj-q8_0.gguf	mmproj-q8_0	848 MB	Download

Qwen3.5-2B-MedVL

File Name	Quant Type	File Size	File Link
Qwen3.5-2B-MedVL.BF16.gguf	BF16	3.78 GB	Download
Qwen3.5-2B-MedVL.F16.gguf	F16	3.78 GB	Download
Qwen3.5-2B-MedVL.F32.gguf	F32	7.54 GB	Download
Qwen3.5-2B-MedVL.Q8_0.gguf	Q8_0	2.01 GB	Download
Qwen3.5-2B-MedVL.mmproj-bf16.gguf	mmproj-bf16	671 MB	Download
Qwen3.5-2B-MedVL.mmproj-f16.gguf	mmproj-f16	671 MB	Download
Qwen3.5-2B-MedVL.mmproj-f32.gguf	mmproj-f32	1.33 GB	Download
Qwen3.5-2B-MedVL.mmproj-q8_0.gguf	mmproj-q8_0	365 MB	Download

Ministral-3B-MedVL

File Name	Quant Type	File Size	File Link
Ministral-3B-MedVL.BF16.gguf	BF16	6.87 GB	Download
Ministral-3B-MedVL.F16.gguf	F16	6.87 GB	Download
Ministral-3B-MedVL.F32.gguf	F32	13.7 GB	Download
Ministral-3B-MedVL.Q8_0.gguf	Q8_0	3.65 GB	Download
Ministral-3B-MedVL.mmproj-bf16.gguf	mmproj-bf16	850 MB	Download
Ministral-3B-MedVL.mmproj-f16.gguf	mmproj-f16	850 MB	Download
Ministral-3B-MedVL.mmproj-f32.gguf	mmproj-f32	1.68 GB	Download
Ministral-3B-MedVL.mmproj-q8_0.gguf	mmproj-q8_0	461 MB	Download

Model Sources

Model Name	Link
OpenMed/Qwen3.5-2B-MedVL	https://huggingface.co/OpenMed/Qwen3.5-2B-MedVL
OpenMed/Qwen2.5-3B-MedVL	https://huggingface.co/OpenMed/Qwen2.5-3B-MedVL
OpenMed/Ministral-3B-MedVL	https://huggingface.co/OpenMed/Ministral-3B-MedVL