Instructions to use smashingtags/eightly-agent with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use smashingtags/eightly-agent with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="smashingtags/eightly-agent",
	filename="eightly-agent-e2b-Q4_K_M.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 smashingtags/eightly-agent with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf smashingtags/eightly-agent:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf smashingtags/eightly-agent:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf smashingtags/eightly-agent:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf smashingtags/eightly-agent:Q4_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 smashingtags/eightly-agent:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf smashingtags/eightly-agent:Q4_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 smashingtags/eightly-agent:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf smashingtags/eightly-agent:Q4_K_M

Use Docker

docker model run hf.co/smashingtags/eightly-agent:Q4_K_M

LM Studio
Jan

vLLM

How to use smashingtags/eightly-agent with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "smashingtags/eightly-agent"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "smashingtags/eightly-agent",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/smashingtags/eightly-agent:Q4_K_M

Ollama
How to use smashingtags/eightly-agent with Ollama:
```
ollama run hf.co/smashingtags/eightly-agent:Q4_K_M
```

Unsloth Studio new

How to use smashingtags/eightly-agent 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 smashingtags/eightly-agent 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 smashingtags/eightly-agent to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for smashingtags/eightly-agent to start chatting

Pi new

How to use smashingtags/eightly-agent with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf smashingtags/eightly-agent:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "eightly-agent"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use smashingtags/eightly-agent with Docker Model Runner:
```
docker model run hf.co/smashingtags/eightly-agent:Q4_K_M
```

Lemonade

How to use smashingtags/eightly-agent with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull smashingtags/eightly-agent:Q4_K_M

Run and chat with the model

lemonade run user.eightly-agent-Q4_K_M

List all available models

lemonade list

Eightly Agent

Tiered model family powering Nova, the built-in AI agent for Eight.ly OS — a self-hosted homelab operating system that combines virtualization, containers, storage, networking, and an AI control plane in a single Go binary.

This repo ships four GGUFs designed to be deployed together. The host OS routes each turn to the right model based on intent and available hardware.

Models

File	Size	Role	Base	Use
`eightly-agent-fg.gguf`	359 MB	Tool router	FunctionGemma 270m	Sub-1s function calls on CPU. Fine-tuned on 4,684 Eight.ly OS tool-calling examples.
`eightly-agent-e2b-Q4_K_M.gguf`	3.2 GB	Conversational	Gemma 4 E2B	Natural chat and reasoning on modest hardware
`eightly-agent-q4b-Q4_K_M.gguf`	2.4 GB	Conversational	Qwen3 4B	Mid-tier homelabs
`eightly-agent-q8b-Q4_K_M.gguf`	4.7 GB	Conversational	Qwen3 8B	Beefy boxes — best reasoning quality

Architecture

Nova uses a dual-mode router: tool-bound turns dispatch to fg for near-instant function calls, while open-ended or reasoning turns go to whichever conversational model fits the host's hardware tier. The OS handles selection automatically — no configuration required.

This means a Pi-class device gets working AI control without GPU, while beefier boxes get richer conversation without sacrificing tool-call latency.

Running

Standard GGUFs — anything that speaks llama.cpp will load them.

With Ollama:

# Pull the function-caller
ollama create eightly-agent-fg -f Modelfile.fg

# Use it
curl http://localhost:11434/api/generate -d '{
  "model": "eightly-agent-fg",
  "prompt": "<bos><start_of_turn>developer\nYou are a model that can do function calling...<start_of_turn>user\nHow much disk space is free?<end_of_turn>\n<start_of_turn>model\n",
  "raw": true,
  "stream": false
}'

With llama.cpp directly:

llama-server -m eightly-agent-fg.gguf --port 8081

Or just run Eight.ly OS and it wires everything up for you.

Tool Calling Format

fg is fine-tuned on FunctionGemma's native format with <start_function_call>call:NAME{args}<end_function_call> tokens. Tool declarations are baked into the prompt as <start_function_declaration>declaration:NAME{...}<end_function_declaration> blocks. The model was trained on 4,684 examples across 41 NAS management tools.

41 Tools

Storage, Docker containers, VMs (KVM/QEMU), LXC, SMB/NFS file sharing, network interfaces, firewall, SnapRAID parity, ZFS pools, SMART health, system info, app store, and more.

Status

Active development. Eight.ly OS is in alpha; this model family is being trained against an evolving 41-tool catalog spanning storage, virtualization, containers, networking, and system control.

Model tree for smashingtags/eightly-agent

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-4B

Quantized

(215)

this model

smashingtags
/

eightly-agent