Instructions to use javierbits/Javi0.4-4B-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 javierbits/Javi0.4-4B-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 javierbits/Javi0.4-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf javierbits/Javi0.4-4B-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 javierbits/Javi0.4-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf javierbits/Javi0.4-4B-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 javierbits/Javi0.4-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf javierbits/Javi0.4-4B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/javierbits/Javi0.4-4B-GGUF:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use javierbits/Javi0.4-4B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "javierbits/Javi0.4-4B-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": "javierbits/Javi0.4-4B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/javierbits/Javi0.4-4B-GGUF:Q4_K_M

Ollama
How to use javierbits/Javi0.4-4B-GGUF with Ollama:
```
ollama run hf.co/javierbits/Javi0.4-4B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use javierbits/Javi0.4-4B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf javierbits/Javi0.4-4B-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": "javierbits/Javi0.4-4B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use javierbits/Javi0.4-4B-GGUF with Docker Model Runner:
```
docker model run hf.co/javierbits/Javi0.4-4B-GGUF:Q4_K_M
```

Lemonade

How to use javierbits/Javi0.4-4B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull javierbits/Javi0.4-4B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Javi0.4-4B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use javierbits/Javi0.4-4B-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 javierbits/Javi0.4-4B-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 javierbits/Javi0.4-4B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use javierbits/Javi0.4-4B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf javierbits/Javi0.4-4B-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 "javierbits/Javi0.4-4B-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"

Javi0.4-4B-GGUF (control)

GGUF quants of Javi0.4-4B, which is Javi0.3-4B with the =open_page embedding row scaled by 0.84. No fine-tuning, no new data, no gradients.

It exists as the 4B control for the Javi0.4 weight-space experiment. It is not an upgrade.

Measured effect

On 8 held-out eval-v3 canonical fail questions with the first web_search forced to fail, Javi0.3-4B already chose web_search in 4/4 cases. The edit changed no measured decision. On an opencode 403 replay, both Javi0.3-4B and Javi0.4-4B fetched another typed URL instead of searching again.

The 4B's remaining recovery gap is in the webfetch/web_fetch route, which this row edit does not reach. Use Javi0.3-4B-GGUF as the recommended 4B. This repo is the reproducible control.

Full eval v3/v3f was not run for Javi0.4.

Files

File	Quant	Size	Notes
`Javi0.4-4B.Q8_0.gguf`	Q8_0	4.3 GB	Close to lossless
`Javi0.4-4B.Q4_K_M.gguf`	Q4_K_M	2.8 GB	Smaller and faster

Both were quantized from an F16 GGUF of the edited merged model. Text only: the base model's vision tower is not in the GGUF.

Run it

llama.cpp

llama-server -hf javierbits/Javi0.4-4B-GGUF:Q8_0 --jinja -c 131072 -fa on -ctk q8_0 -ctv q8_0 \
  --chat-template-kwargs '{"enable_thinking": false}' \
  --temp 0.2 --top-p 0.8 --top-k 20 --min-p 0

lmdeck