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

Libraries

How to use tehinkage/GenMediaStudio with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tehinkage/GenMediaStudio",
	filename="GenMediaResource/ai/Hy-MT2-1.8B-Q4_K_M.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 tehinkage/GenMediaStudio 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 tehinkage/GenMediaStudio:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf tehinkage/GenMediaStudio:Q4_K_M

Install from WinGet (Windows)

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

Use Docker

docker model run hf.co/tehinkage/GenMediaStudio:Q4_K_M

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

Unsloth Studio

How to use tehinkage/GenMediaStudio 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 tehinkage/GenMediaStudio 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 tehinkage/GenMediaStudio to start chatting

Using HuggingFace Spaces for Unsloth

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

How to use tehinkage/GenMediaStudio with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tehinkage/GenMediaStudio:Q4_K_M

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": "tehinkage/GenMediaStudio:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use tehinkage/GenMediaStudio with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tehinkage/GenMediaStudio:Q4_K_M

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 tehinkage/GenMediaStudio:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use tehinkage/GenMediaStudio with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tehinkage/GenMediaStudio:Q4_K_M

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 "tehinkage/GenMediaStudio:Q4_K_M" \
  --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 tehinkage/GenMediaStudio with Docker Model Runner:
```
docker model run hf.co/tehinkage/GenMediaStudio:Q4_K_M
```

Lemonade

How to use tehinkage/GenMediaStudio with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tehinkage/GenMediaStudio:Q4_K_M

Run and chat with the model

lemonade run user.GenMediaStudio-Q4_K_M

List all available models

lemonade list

GenMedia Studio Resources

This repository contains resource packages used by GenMedia Studio.

These resources are downloaded automatically by the application when needed.

Repository Contents

Resources in this repository may include:

AI models
ASR engines
TTS engines
Fonts
Runtime assets
Configuration files
Other application resources

License Notice

This repository contains both original GenMedia Studio content and third-party resources.

Original files created specifically for GenMedia Studio are owned by TehinKage.

Third-party models, engines, fonts, datasets, checkpoints and other software remain the property of their respective authors and continue to be governed by their original licenses.

Nothing in this repository modifies, replaces or overrides the license of any third-party component.

Third-party Projects

Examples include (but are not limited to):

Faster Whisper
SenseVoice
OmniVoice
NghiTTS
Other open-source projects

Please refer to each project's official repository for licensing information.

Redistribution

If you redistribute any resources from this repository, you are responsible for complying with the original license of each included component.

Disclaimer

All resources are provided AS IS, without warranty of any kind.

Downloads last month: 35

GGUF

Model size

8B params

Architecture

gemma4

Hardware compatibility

4-bit

Inference Providers NEW

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