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": "smashingtags/eightly-agent:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use smashingtags/eightly-agent with Hermes Agent:

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 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 smashingtags/eightly-agent:Q4_K_M

Run Hermes

hermes

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

Eight.ly Agent

Fine-tuned on 4,684 Eight.ly OS tool-calling examples across 41 NAS management tools (Docker, storage, VMs, LXC, file sharing, system administration).

Architecture

user query
    |
    v
+---------------+
| Nova Router   |
| (Go intent    |
|  classifier)  |
+-------+-------+
        |
   +----+----+
   v         v
+------+  +----------------+
| fg   |  | conversational |
|359MB |  | tier (gemma2,  |
|tool  |  | q4b, q8b, e2b) |
|calls |  |                |
+------+  +----------------+

The Nova Router is a zero-latency Go pattern matcher (57 test cases) that classifies queries into no_tool, tool, or maybe. Tool queries route to FunctionGemma for structured tool-call extraction via GBNF grammar. Conversational queries skip directly to the response model.

Evaluation

Metric	Value
Tool-call accuracy (fg)	87.5% (13/15 standard audit suite)
FunctionGemma latency	Sub-1s on CPU
Median tool-query response	6.9s end-to-end
No-tool response time	1-3s
System queries	10-18s
Container/health queries	6-14s

Evaluated by Opus 4.7 auditor over 8 rounds. Remaining sharp edges: Docker stop/kill semantics, acknowledgment over-eagerness, storage pool labeling.

Models

Model	Base	GGUF Size	Role
eightly-agent-fg	FunctionGemma 270M	359 MB	Tool router (dual-model worker)
eightly-agent-q4b	Qwen3 4B	2.4 GB	Single-model fallback
eightly-agent-q8b	Qwen3 8B	4.7 GB	Best single-model quality
eightly-agent-e2b	Gemma 4 E2B	3.2 GB	Experimental (not yet deployed)

Conversational tier uses stock gemma2:2b (1.6 GB) as the response synthesizer.

Training Data

4,684 tool-calling examples (FunctionGemma fine-tune)
41 tools across 6 domains: Docker, Storage, VMs, LXC, File Sharing, System
Dataset: smashingtags/eightly-agent-dataset

Usage

# Pull the FunctionGemma tool router
ollama pull smashingtags/eightly-agent-fg

# Pull the single-model fallback (Qwen3 4B)
ollama pull smashingtags/eightly-agent-q4b

# Pull the high-quality single-model (Qwen3 8B)
ollama pull smashingtags/eightly-agent-q8b

# Run locally
ollama run smashingtags/eightly-agent-q4b

These models are designed to work within the Eight.ly OS Nova assistant pipeline. FunctionGemma expects a scoped tool catalog with GBNF grammar constraints. The q4b/q8b models support native Ollama tool calling.

Example: Tool-Calling Flow

User: "How much disk space is free?"

Step 1 — FunctionGemma routes to tool:

<start_function_call>call:get_storage_status{}<end_function_call>

Step 2 — Tool executes, returns real data:

{"mountpoint": "/mnt/storage", "total": "69.8 GB", "used": "22 MB", "free": "69.8 GB", "percent": "0.03%"}

Step 3 — Conversational model responds:

"Your storage pool at /mnt/storage has 69.8 GB free out of 69.8 GB total — essentially empty at 0.03% used."

End-to-end: ~6.9 seconds median. FunctionGemma decision: sub-1 second.

41 Tools

Docker: list_containers, get_container_logs, get_container_stats, list_docker_stacks, list_docker_images, list_docker_networks, list_docker_volumes, container_action, pull_docker_image, install_app

Storage: get_storage_status, get_storage_capacity, get_cache_status, get_snapraid_status, get_disk_health, get_zfs_pools, run_snapraid_sync, run_smart_test, spin_down_disks, create_backup

VMs: list_vms, get_vm_stats, list_vm_snapshots, vm_action, create_vm_snapshot

LXC: list_lxc_containers, lxc_action

File Sharing: get_smb_shares, get_nfs_exports, create_smb_share, create_nfs_export

System: get_system_info, get_system_version, get_system_logs, get_node_time, get_network_interfaces, get_firewall_rules, get_health_overview, get_nova_models, search_apps, set_timezone, reboot_system

Roadmap

Tool catalog growing from 41 tools. Next: scheduling tools, backup management, network diagnostics.
Multi-turn context for follow-up questions.
Additional domain scoping refinements based on real user feedback.
Gemma 4 E2B deployment and evaluation.

License

Apache 2.0

Downloads last month: 1,169

GGUF

Model size

5B params

Architecture

gemma4

Hardware compatibility

4-bit

View +1 variant

smashingtags
/

eightly-agent

Eight.ly Agent

Architecture

Evaluation

Models

Training Data

Usage

Example: Tool-Calling Flow

41 Tools

Roadmap

Links

License