Instructions to use DojoWorkspace/Dojo-Small-v1.0-E4B-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 DojoWorkspace/Dojo-Small-v1.0-E4B-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 DojoWorkspace/Dojo-Small-v1.0-E4B-gguf:Q4_0
# Run inference directly in the terminal:
llama cli -hf DojoWorkspace/Dojo-Small-v1.0-E4B-gguf:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf DojoWorkspace/Dojo-Small-v1.0-E4B-gguf:Q4_0
# Run inference directly in the terminal:
llama cli -hf DojoWorkspace/Dojo-Small-v1.0-E4B-gguf:Q4_0

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf DojoWorkspace/Dojo-Small-v1.0-E4B-gguf:Q4_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf DojoWorkspace/Dojo-Small-v1.0-E4B-gguf:Q4_0

Use Docker

docker model run hf.co/DojoWorkspace/Dojo-Small-v1.0-E4B-gguf:Q4_0

Llama new
LM Studio
Jan

vLLM

How to use DojoWorkspace/Dojo-Small-v1.0-E4B-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DojoWorkspace/Dojo-Small-v1.0-E4B-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": "DojoWorkspace/Dojo-Small-v1.0-E4B-gguf",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/DojoWorkspace/Dojo-Small-v1.0-E4B-gguf:Q4_0

Ollama
How to use DojoWorkspace/Dojo-Small-v1.0-E4B-gguf with Ollama:
```
ollama run hf.co/DojoWorkspace/Dojo-Small-v1.0-E4B-gguf:Q4_0
```
Unsloth Desktop

How to use DojoWorkspace/Dojo-Small-v1.0-E4B-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf DojoWorkspace/Dojo-Small-v1.0-E4B-gguf:Q4_0

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": "DojoWorkspace/Dojo-Small-v1.0-E4B-gguf:Q4_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use DojoWorkspace/Dojo-Small-v1.0-E4B-gguf with Docker Model Runner:
```
docker model run hf.co/DojoWorkspace/Dojo-Small-v1.0-E4B-gguf:Q4_0
```

Lemonade

How to use DojoWorkspace/Dojo-Small-v1.0-E4B-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull DojoWorkspace/Dojo-Small-v1.0-E4B-gguf:Q4_0

Run and chat with the model

lemonade run user.Dojo-Small-v1.0-E4B-gguf-Q4_0

List all available models

lemonade list

Hermes Agent

How to use DojoWorkspace/Dojo-Small-v1.0-E4B-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 DojoWorkspace/Dojo-Small-v1.0-E4B-gguf:Q4_0

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 DojoWorkspace/Dojo-Small-v1.0-E4B-gguf:Q4_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use DojoWorkspace/Dojo-Small-v1.0-E4B-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf DojoWorkspace/Dojo-Small-v1.0-E4B-gguf:Q4_0

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 "DojoWorkspace/Dojo-Small-v1.0-E4B-gguf:Q4_0" \
  --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"

Dojo-Small v1.0 (E4B)

An on-device chat model used by Dojo for local tool calling and image understanding, one size up from Dojo-Tiny.

Dojo-Small v1.0 is google/gemma-4-E4B-it, unmodified, quantized to GGUF and renamed for Dojo. No fine-tuning. The GGUF files are byte-identical to ggml-org/gemma-4-E4B-it-GGUF at commit a69f018d7678a2b9f5e705f8903d6fb29b9b25dc. All credit for the model belongs to Google DeepMind.

Files

File	Quantization	Purpose
`Dojo-Small-v1.0-E4B-Q4_0.gguf`	Q4_0	Language model (text + tool calls)
`mmproj-Dojo-Small-v1.0-E4B-Q8_0.gguf`	Q8_0	Vision projector (images)

Context length

Up to 128K tokens (131,072). Dojo sizes the working context to the memory available on each device, scaling it up or down as needed.

License

Apache License 2.0, the same as the upstream Gemma 4 model. See the upstream model card for intended use and limitations.

Downloads last month: 118

GGUF

Model size

7B params

Architecture

gemma4

Hardware compatibility

4-bit

Model tree for DojoWorkspace/Dojo-Small-v1.0-E4B-gguf

Base model

google/gemma-4-E4B

Finetuned

google/gemma-4-E4B-it

Quantized

(422)

this model