Instructions to use Spyt1k/AstralX-Coder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Spyt1k/AstralX-Coder 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 Spyt1k/AstralX-Coder
# Run inference directly in the terminal:
llama cli -hf Spyt1k/AstralX-Coder

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Spyt1k/AstralX-Coder
# Run inference directly in the terminal:
llama cli -hf Spyt1k/AstralX-Coder

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 Spyt1k/AstralX-Coder
# Run inference directly in the terminal:
./build/bin/llama cli -hf Spyt1k/AstralX-Coder

Use Docker

docker model run hf.co/Spyt1k/AstralX-Coder

Llama new
LM Studio
Jan
Ollama
How to use Spyt1k/AstralX-Coder with Ollama:
```
ollama run hf.co/Spyt1k/AstralX-Coder
```
Unsloth Desktop

How to use Spyt1k/AstralX-Coder with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Spyt1k/AstralX-Coder

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": "Spyt1k/AstralX-Coder"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Spyt1k/AstralX-Coder with Docker Model Runner:
```
docker model run hf.co/Spyt1k/AstralX-Coder
```

Lemonade

How to use Spyt1k/AstralX-Coder with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Spyt1k/AstralX-Coder

Run and chat with the model

lemonade run user.AstralX-Coder-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use Spyt1k/AstralX-Coder with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Spyt1k/AstralX-Coder

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 Spyt1k/AstralX-Coder

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Spyt1k/AstralX-Coder with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Spyt1k/AstralX-Coder

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 "Spyt1k/AstralX-Coder" \
  --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"

AstralX 3B

AstralX is a lightweight, specialized code-assistant model fine-tuned on top of Qwen2.5-Coder-3B-Instruct.

It is designed to act as an efficient, low-latency secondary AI copilot directly in your local development environment or CLI setup. While it might not outsmart massive frontier models on complex architecture design, it serves as an excellent, fast companion for everyday coding tasks, refactoring, and autocomplete.

🚀 Model Details

Base Model: Qwen2.5-Coder-3B-Instruct
Parameters: 3 Billion
Fine-tuning Dataset: 6,000+ curated, high-quality code samples extracted and filtered from top-tier frontier models (Claude 3.5 Sonnet, Gemini 1.5 Pro, DeepSeek-V3, Qwen-Max, GLM-4).
Primary Focus: High-quality syntax, idiomatic patterns, and optimal formatting.

📚 Supported Languages

The dataset was specially curated to boost performance in the following languages:

🦀 Rust (Idiomatic memory management, ownership patterns, and CLI tools)
🐍 Python (Scripts, automation, backend logic)
🌙 Lua (Game scripting, Neovim configs, embeds)
☕ Java (Object-oriented architecture, clean code templates)
🌐 JavaScript (Modern ES6+, web tools)

💡 Use Case & Philosophy

AstralX doesn't aim to be a "know-it-all" general intelligence. It was built with the "vibe-coding" philosophy in mind—providing high-speed, localized assistance. It works perfectly as an auxiliary tool running locally via Ollama or embedded directly into text editors.

🛠️ How to Use with Ollama (GGUF)

If you are using the GGUF version with the provided Modelfile, you can run it locally via:

ollama create AstralX -f ./Modelfile
ollama run AstralX

Fine-tuned with love for high-speed terminal and editor workflows.

Downloads last month: 48

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Spyt1k/AstralX-Coder

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-Coder-3B

Finetuned

Qwen/Qwen2.5-Coder-3B-Instruct

Adapter

(95)

this model