Instructions to use GPT4All-Community/phi-4-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use GPT4All-Community/phi-4-GGUF with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="GPT4All-Community/phi-4-GGUF") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("GPT4All-Community/phi-4-GGUF", dtype="auto") - llama-cpp-python
How to use GPT4All-Community/phi-4-GGUF with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="GPT4All-Community/phi-4-GGUF", filename="phi-4-Q4_0.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use GPT4All-Community/phi-4-GGUF with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf GPT4All-Community/phi-4-GGUF:Q4_0 # Run inference directly in the terminal: llama-cli -hf GPT4All-Community/phi-4-GGUF:Q4_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf GPT4All-Community/phi-4-GGUF:Q4_0 # Run inference directly in the terminal: llama-cli -hf GPT4All-Community/phi-4-GGUF:Q4_0
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 GPT4All-Community/phi-4-GGUF:Q4_0 # Run inference directly in the terminal: ./llama-cli -hf GPT4All-Community/phi-4-GGUF:Q4_0
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 GPT4All-Community/phi-4-GGUF:Q4_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf GPT4All-Community/phi-4-GGUF:Q4_0
Use Docker
docker model run hf.co/GPT4All-Community/phi-4-GGUF:Q4_0
- LM Studio
- Jan
- vLLM
How to use GPT4All-Community/phi-4-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "GPT4All-Community/phi-4-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": "GPT4All-Community/phi-4-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/GPT4All-Community/phi-4-GGUF:Q4_0
- SGLang
How to use GPT4All-Community/phi-4-GGUF with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "GPT4All-Community/phi-4-GGUF" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "GPT4All-Community/phi-4-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "GPT4All-Community/phi-4-GGUF" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "GPT4All-Community/phi-4-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Ollama
How to use GPT4All-Community/phi-4-GGUF with Ollama:
ollama run hf.co/GPT4All-Community/phi-4-GGUF:Q4_0
- Unsloth Studio new
How to use GPT4All-Community/phi-4-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 GPT4All-Community/phi-4-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 GPT4All-Community/phi-4-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for GPT4All-Community/phi-4-GGUF to start chatting
- Docker Model Runner
How to use GPT4All-Community/phi-4-GGUF with Docker Model Runner:
docker model run hf.co/GPT4All-Community/phi-4-GGUF:Q4_0
- Lemonade
How to use GPT4All-Community/phi-4-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull GPT4All-Community/phi-4-GGUF:Q4_0
Run and chat with the model
lemonade run user.phi-4-GGUF-Q4_0
List all available models
lemonade list
Failed to parse chat template
I'm seeing this on download
{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|><|im_start|>assistant<|im_sep|>'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}
But i'm seeing Syntax error: 1:136 Unexpected token '}'. Expected '>'.
Not quite seeing the issue, but this also seems like the old chat template: https://docs.gpt4all.io/gpt4all_desktop/chat_templates.html#what-changed-in-gpt4all-v35
When using this model with GPT4All
{{- '<|im_start|>system<|im_sep|>' }}
{% if toolList|length > 0 %}You have access to the following functions:
{% for tool in toolList %}
Use the function '{{tool.function}}' to: '{{tool.description}}'
{% if tool.parameters|length > 0 %}
parameters:
{% for info in tool.parameters %}
{{info.name}}:
type: {{info.type}}
description: {{info.description}}
required: {{info.required}}
{% endfor %}
{% endif %}
# Tool Instructions
If you CHOOSE to call this function ONLY reply with the following format:
'{{tool.symbolicFormat}}'
Here is an example. If the user says, '{{tool.examplePrompt}}', then you reply
'{{tool.exampleCall}}'
After the result you might reply with, '{{tool.exampleReply}}'
{% endfor %}
You MUST include both the start and end tags when you use a function.
You are a helpful AI assistant who uses the functions to break down, analyze, perform, and verify complex reasoning tasks. You SHOULD try to verify your answers using the functions where possible.
{% endif %}
{{- '<|im_end|>' }}
{% for message in messages %}
{% if (message['role'] == 'system') %}
{{ '<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>' }}
{% elif (message['role'] == 'user') %}
{{ '<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|><|im_start|>assistant<|im_sep|>' }}
{% elif (message['role'] == 'assistant') %}
{{ message['content'] + '<|im_end|>' }}
{% endif %}
{% endfor %}
I'm seeing this on download
Yes the original template is in the gguf, the one you want to use is now above.
But i'm seeing
Syntax error: 1:136 Unexpected token '}'. Expected '>'.
Because the original template is not formatted for GPT4All, and the model has not been uploaded officially yet. If it is included as an official supported model the template will be changed by GPT4All.
the template you've shared is working, thank you!