Instructions to use nabin2004/AOS-gemma4-manim-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 nabin2004/AOS-gemma4-manim-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 nabin2004/AOS-gemma4-manim-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf nabin2004/AOS-gemma4-manim-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 nabin2004/AOS-gemma4-manim-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf nabin2004/AOS-gemma4-manim-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 nabin2004/AOS-gemma4-manim-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf nabin2004/AOS-gemma4-manim-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 nabin2004/AOS-gemma4-manim-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf nabin2004/AOS-gemma4-manim-gguf:Q4_K_M

Use Docker

docker model run hf.co/nabin2004/AOS-gemma4-manim-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use nabin2004/AOS-gemma4-manim-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nabin2004/AOS-gemma4-manim-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": "nabin2004/AOS-gemma4-manim-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nabin2004/AOS-gemma4-manim-gguf:Q4_K_M

Ollama
How to use nabin2004/AOS-gemma4-manim-gguf with Ollama:
```
ollama run hf.co/nabin2004/AOS-gemma4-manim-gguf:Q4_K_M
```

Unsloth Studio

How to use nabin2004/AOS-gemma4-manim-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 nabin2004/AOS-gemma4-manim-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 nabin2004/AOS-gemma4-manim-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for nabin2004/AOS-gemma4-manim-gguf to start chatting

How to use nabin2004/AOS-gemma4-manim-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nabin2004/AOS-gemma4-manim-gguf: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": "nabin2004/AOS-gemma4-manim-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use nabin2004/AOS-gemma4-manim-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 nabin2004/AOS-gemma4-manim-gguf: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 nabin2004/AOS-gemma4-manim-gguf:Q4_K_M

Run Hermes

hermes

OpenClaw new

How to use nabin2004/AOS-gemma4-manim-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nabin2004/AOS-gemma4-manim-gguf: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 "nabin2004/AOS-gemma4-manim-gguf: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 nabin2004/AOS-gemma4-manim-gguf with Docker Model Runner:
```
docker model run hf.co/nabin2004/AOS-gemma4-manim-gguf:Q4_K_M
```

Lemonade

How to use nabin2004/AOS-gemma4-manim-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull nabin2004/AOS-gemma4-manim-gguf:Q4_K_M

Run and chat with the model

lemonade run user.AOS-gemma4-manim-gguf-Q4_K_M

List all available models

lemonade list

Atomic Chat

AOS Gemma 4 Manim SFT (GGUF)

Q4_K_M GGUF of the AOS Manim SFT merged model. Drop-in for Ollama and llama.cpp.

Model URL: https://huggingface.co/nabin2004/AOS-gemma4-manim-gguf

Files

File	Description
`aos-gemma4-manim-Q4_K_M.gguf`	Quantized weights (~2 GB for E2B)
`Modelfile`	Ollama import template

Related repos

Artifact	Repo
LoRA adapter	nabin2004/AOS-gemma4-manim-sft
Merged HF weights	nabin2004/AOS-gemma4-manim-merged

Ollama

Pull from Hugging Face or create locally from the downloaded GGUF:

ollama create aos-gemma4-manim -f Modelfile
ollama run aos-gemma4-manim

Requires Ollama 0.30+ (native Gemma 4 support).

OpenAI-compatible API

Ollama exposes /v1/chat/completions on port 11434:

from gemma4_client import DEFAULT_OLLAMA_BASE_URL, Gemma4Client

client = Gemma4Client(
    model="aos-gemma4-manim",
    base_url=DEFAULT_OLLAMA_BASE_URL,
    api_key="ollama",
)
print(client.chat("Animate a unit circle morphing into an ellipse."))

See apps/server/README.md.

llama.cpp

./llama-server -m aos-gemma4-manim-Q4_K_M.gguf --chat-template gemma --port 8080

How this was produced

cd apps/sft
export LLAMA_CPP_DIR=~/llama.cpp
uv run python export_gguf.py \
  --model-dir ./gemma4-manim-merged \
  --output-dir ./gemma4-manim-gguf \
  --push-to-hub

Quantization chain: merge_adapter.py → convert_hf_to_gguf.py (F16) → llama-quantize Q4_K_M.

Downloads last month: 153

GGUF

Model size

5B params

Architecture

gemma4

Hardware compatibility

4-bit