Instructions to use Dolphy-AI/Dolphy-1.0-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 Dolphy-AI/Dolphy-1.0-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 Dolphy-AI/Dolphy-1.0-GGUF:Q5_K_M
# Run inference directly in the terminal:
llama cli -hf Dolphy-AI/Dolphy-1.0-GGUF:Q5_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Dolphy-AI/Dolphy-1.0-GGUF:Q5_K_M
# Run inference directly in the terminal:
llama cli -hf Dolphy-AI/Dolphy-1.0-GGUF:Q5_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 Dolphy-AI/Dolphy-1.0-GGUF:Q5_K_M
# Run inference directly in the terminal:
./llama-cli -hf Dolphy-AI/Dolphy-1.0-GGUF:Q5_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 Dolphy-AI/Dolphy-1.0-GGUF:Q5_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Dolphy-AI/Dolphy-1.0-GGUF:Q5_K_M

Use Docker

docker model run hf.co/Dolphy-AI/Dolphy-1.0-GGUF:Q5_K_M

LM Studio
Jan

vLLM

How to use Dolphy-AI/Dolphy-1.0-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Dolphy-AI/Dolphy-1.0-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": "Dolphy-AI/Dolphy-1.0-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Dolphy-AI/Dolphy-1.0-GGUF:Q5_K_M

Ollama
How to use Dolphy-AI/Dolphy-1.0-GGUF with Ollama:
```
ollama run hf.co/Dolphy-AI/Dolphy-1.0-GGUF:Q5_K_M
```
Unsloth Desktop

How to use Dolphy-AI/Dolphy-1.0-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Dolphy-AI/Dolphy-1.0-GGUF:Q5_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": "Dolphy-AI/Dolphy-1.0-GGUF:Q5_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Dolphy-AI/Dolphy-1.0-GGUF with Docker Model Runner:
```
docker model run hf.co/Dolphy-AI/Dolphy-1.0-GGUF:Q5_K_M
```

Lemonade

How to use Dolphy-AI/Dolphy-1.0-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Dolphy-AI/Dolphy-1.0-GGUF:Q5_K_M

Run and chat with the model

lemonade run user.Dolphy-1.0-GGUF-Q5_K_M

List all available models

lemonade list

Hermes Agent

How to use Dolphy-AI/Dolphy-1.0-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 Dolphy-AI/Dolphy-1.0-GGUF:Q5_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 Dolphy-AI/Dolphy-1.0-GGUF:Q5_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Dolphy-AI/Dolphy-1.0-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Dolphy-AI/Dolphy-1.0-GGUF:Q5_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 "Dolphy-AI/Dolphy-1.0-GGUF:Q5_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"

Dolphy-1.0-GGUF

Dolphy AI's First step into the world of Machine Learning.

This is a fine tune of Qwen 3 4B 2507 Instruct, a lightweight but capable model that can outperform many larger models. We used Unsloth LoRA Finetuning on an extensive range of high quality diverse datasets. Dolphy 1.0 was fine tuned on 1.5M examples throughout it's fine tuning pipeline.

Dolphy 1.0 was trained in 20 different datasets, with 1.5M examples in total. Every dataset was carefully curated to extend the Qwen's behaviour to create a Small Model with Superior dominance over the 4B catagory.

Compatibility

As Dolphy 1.0 and Qwen3 2507 Instruct models share the same base, Dolphy 1.0 is compatible with Qwen3's extensive tool use, function calling and multilingual capibilities. The tokenizer is unchanged and the model archetecture is intact. You can also find this model in upcoming Dolphy AI releases.

Example usage:

For Llama.CPP: llama-cli --hf Dolphy-AI/Dolphy-1.0-GGUF -p "What is a Dolphin?"

You can also find this model in upcoming Dolphy AI releases.

Available Model files:

DolphyAI-1.0-Q5_K_M.gguf

Downloads last month: 97

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

2-bit

5-bit

Model tree for Dolphy-AI/Dolphy-1.0-GGUF

Base model

Qwen/Qwen3-4B-Instruct-2507

Finetuned

Dolphy-AI/Dolphy-1.0

Quantized

(6)

this model

Collection including Dolphy-AI/Dolphy-1.0-GGUF

Dolphy 1.0 Release

Collection

Our First push towards an on-device future. • 2 items • Updated Oct 15, 2025