Instructions to use DojoWorkspace/Dojo-Tiny-v1.0-4B-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-Tiny-v1.0-4B-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-Tiny-v1.0-4B-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf DojoWorkspace/Dojo-Tiny-v1.0-4B-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 DojoWorkspace/Dojo-Tiny-v1.0-4B-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf DojoWorkspace/Dojo-Tiny-v1.0-4B-gguf:Q4_K_M

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-Tiny-v1.0-4B-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf DojoWorkspace/Dojo-Tiny-v1.0-4B-gguf:Q4_K_M

Use Docker

docker model run hf.co/DojoWorkspace/Dojo-Tiny-v1.0-4B-gguf:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use DojoWorkspace/Dojo-Tiny-v1.0-4B-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DojoWorkspace/Dojo-Tiny-v1.0-4B-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-Tiny-v1.0-4B-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-Tiny-v1.0-4B-gguf:Q4_K_M

Ollama
How to use DojoWorkspace/Dojo-Tiny-v1.0-4B-gguf with Ollama:
```
ollama run hf.co/DojoWorkspace/Dojo-Tiny-v1.0-4B-gguf:Q4_K_M
```
Unsloth Desktop

How to use DojoWorkspace/Dojo-Tiny-v1.0-4B-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-Tiny-v1.0-4B-gguf:Q4_K_M

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-Tiny-v1.0-4B-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use DojoWorkspace/Dojo-Tiny-v1.0-4B-gguf with Docker Model Runner:
```
docker model run hf.co/DojoWorkspace/Dojo-Tiny-v1.0-4B-gguf:Q4_K_M
```

Lemonade

How to use DojoWorkspace/Dojo-Tiny-v1.0-4B-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull DojoWorkspace/Dojo-Tiny-v1.0-4B-gguf:Q4_K_M

Run and chat with the model

lemonade run user.Dojo-Tiny-v1.0-4B-gguf-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use DojoWorkspace/Dojo-Tiny-v1.0-4B-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-Tiny-v1.0-4B-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 DojoWorkspace/Dojo-Tiny-v1.0-4B-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use DojoWorkspace/Dojo-Tiny-v1.0-4B-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-Tiny-v1.0-4B-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 "DojoWorkspace/Dojo-Tiny-v1.0-4B-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"

Dojo-Tiny v1.0 (4B)

The smallest on-device chat model used by Dojo for local tool calling, long context and image understanding.

Dojo-Tiny v1.0 is Qwen/Qwen3.5-4B, unmodified, quantized to GGUF and renamed for Dojo. No fine-tuning. The GGUF files are byte-identical to unsloth/Qwen3.5-4B-GGUF at commit e87f176479d0855a907a41277aca2f8ee7a09523. All credit for the model belongs to the Qwen team at Alibaba Cloud; quantization by Unsloth.

Files

File	Quantization	Purpose
`Dojo-Tiny-v1.0-4B-Q4_K_M.gguf`	Q4_K_M	Language model (text + tool calls)
`mmproj-Dojo-Tiny-v1.0-4B-F16.gguf`	F16	Vision projector (images)

Context length

Up to 262K tokens (262,144). 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 Qwen3.5 model. See the upstream model card for intended use and limitations.

Downloads last month: 130

GGUF

Model size

4B params

Architecture

qwen35

Hardware compatibility

4-bit

Model tree for DojoWorkspace/Dojo-Tiny-v1.0-4B-gguf

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Quantized

(604)

this model