Instructions to use TheBioHub/gemma4-e4b-arcade-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 TheBioHub/gemma4-e4b-arcade-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 TheBioHub/gemma4-e4b-arcade-gguf:Q6_K
# Run inference directly in the terminal:
llama cli -hf TheBioHub/gemma4-e4b-arcade-gguf:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf TheBioHub/gemma4-e4b-arcade-gguf:Q6_K
# Run inference directly in the terminal:
llama cli -hf TheBioHub/gemma4-e4b-arcade-gguf:Q6_K

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 TheBioHub/gemma4-e4b-arcade-gguf:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf TheBioHub/gemma4-e4b-arcade-gguf:Q6_K

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 TheBioHub/gemma4-e4b-arcade-gguf:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TheBioHub/gemma4-e4b-arcade-gguf:Q6_K

Use Docker

docker model run hf.co/TheBioHub/gemma4-e4b-arcade-gguf:Q6_K

LM Studio
Jan

vLLM

How to use TheBioHub/gemma4-e4b-arcade-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBioHub/gemma4-e4b-arcade-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": "TheBioHub/gemma4-e4b-arcade-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TheBioHub/gemma4-e4b-arcade-gguf:Q6_K

Ollama
How to use TheBioHub/gemma4-e4b-arcade-gguf with Ollama:
```
ollama run hf.co/TheBioHub/gemma4-e4b-arcade-gguf:Q6_K
```
Unsloth Desktop

How to use TheBioHub/gemma4-e4b-arcade-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TheBioHub/gemma4-e4b-arcade-gguf:Q6_K

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "TheBioHub/gemma4-e4b-arcade-gguf:Q6_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use TheBioHub/gemma4-e4b-arcade-gguf with Docker Model Runner:
```
docker model run hf.co/TheBioHub/gemma4-e4b-arcade-gguf:Q6_K
```

Lemonade

How to use TheBioHub/gemma4-e4b-arcade-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TheBioHub/gemma4-e4b-arcade-gguf:Q6_K

Run and chat with the model

lemonade run user.gemma4-e4b-arcade-gguf-Q6_K

List all available models

lemonade list

Hermes Agent

How to use TheBioHub/gemma4-e4b-arcade-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 TheBioHub/gemma4-e4b-arcade-gguf:Q6_K

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 TheBioHub/gemma4-e4b-arcade-gguf:Q6_K

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use TheBioHub/gemma4-e4b-arcade-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TheBioHub/gemma4-e4b-arcade-gguf:Q6_K

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 "TheBioHub/gemma4-e4b-arcade-gguf:Q6_K" \
  --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"

gemma4-e4b-arcade-GGUF

Gemma 4 E4B, LoRA fine-tuned for ARCade (ARC aid via AI): run the Griffin nanopore preprocessing pipeline (Dorado basecalling, demultiplexing, FASTQ, FastQC/NanoPlot/MultiQC) on the University of Calgary ARC cluster by chatting.

ARCade downloads this file itself; you do not need to fetch it by hand.

Files

File	Size	MD5
`gemma4-e4b-arcade-Q6_K.gguf`	6,172,078,912 B	`60305388062e2afea94e06ef52c66bde`

Prompt format

ARCade renders the chat template itself and calls llama.cpp's /completion endpoint. Tool calls come out as

<|tool_call>call:TOOL_NAME{{"arg": "value"}}<tool_call|>

Training

Base: google/gemma-4-e4b-it, snapshot fee6332c1abaafb77f6f9624236c63aa2f1d0187.
LoRA with mlx-lm 0.31.3: rank 16, 16 layers, 640 iterations, batch 4, lr 1e-4.
Data: 1,264 synthetic multi-turn conversations. They cover the one-command workflow, the four steps run one at a time, job status, results, resources, and the questions participants ask.
Merged, converted with convert_hf_to_gguf.py --outtype f16, quantized with llama-quantize Q6_K. Q6_K, not Q4_K_M: on 60 held-out turns Q6_K matched the f16 model (48 vs 47 exact), Q4_K_M dropped to 37.

License

Apache 2.0, inherited from google/gemma-4-e4b-it.

Downloads last month: 97

GGUF

Model size

7B params

Architecture

gemma4

Hardware compatibility

6-bit