Instructions to use ErebusTN/Athena-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 ErebusTN/Athena-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 ErebusTN/Athena-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ErebusTN/Athena-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 ErebusTN/Athena-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ErebusTN/Athena-GGUF: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 ErebusTN/Athena-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ErebusTN/Athena-GGUF: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 ErebusTN/Athena-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ErebusTN/Athena-GGUF:Q4_K_M

Use Docker

docker model run hf.co/ErebusTN/Athena-GGUF:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use ErebusTN/Athena-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ErebusTN/Athena-GGUF:Q4_K_M

Ollama
How to use ErebusTN/Athena-GGUF with Ollama:
```
ollama run hf.co/ErebusTN/Athena-GGUF:Q4_K_M
```
Unsloth Desktop

How to use ErebusTN/Athena-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ErebusTN/Athena-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": "ErebusTN/Athena-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ErebusTN/Athena-GGUF with Docker Model Runner:
```
docker model run hf.co/ErebusTN/Athena-GGUF:Q4_K_M
```

Lemonade

How to use ErebusTN/Athena-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ErebusTN/Athena-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Athena-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use ErebusTN/Athena-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 ErebusTN/Athena-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 ErebusTN/Athena-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ErebusTN/Athena-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ErebusTN/Athena-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 "ErebusTN/Athena-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"

🦉 Athena · GGUF

Compact intelligence for CPUs, laptops and phones.

Quantized builds of Athena by ErebusTN at EGen Labs

📦 Files

File	Quant	Size	Notes
`Athena-F16.gguf`	F16	3.47 GB	full-precision reference
`Athena-Q8_0.gguf`	Q8_0	1.85 GB	near-lossless
`Athena-Q6_K.gguf`	Q6_K	1.43 GB	high quality
`Athena-Q5_K_M.gguf`	Q5_K_M	1.26 GB	balanced
`Athena-Q4_K_M.gguf`	Q4_K_M	1.10 GB	recommended default

Which one should I pick?

Q4_K_M is the best default for phones and laptops: smallest size with good quality.
Q5_K_M / Q6_K trade a little size for quality.
Q8_0 is close to lossless.
F16 is the full-precision reference.

⚡ Run it

# one-liner: download and chat
llama-cli -hf ErebusTN/Athena-GGUF:Q4_K_M \
  --temp 0.1 --top-k 50 --repeat-penalty 1.1 --reasoning off

# or serve an OpenAI-compatible API
llama-server -hf ErebusTN/Athena-GGUF:Q4_K_M --reasoning off

Sampling: temperature 0.1, top_k 50, repeat_penalty 1.1.
Identity prompt: the chat template embedded in these files uses Athena's identity prompt as the default system message and starts in non-thinking mode. Passing your own system message overrides the default.
Thinking: --reasoning off keeps thinking disabled even if your runtime would otherwise turn it on.

ℹ️ About Athena

Athena is EGen Labs' compact, security-fluent assistant: direct answers, honest about what it doesn't know, no internet, no memory across conversations. See the main model card for the training recipe, evaluation, intended use and limitations.

Safety note: Athena can be wrong, especially on CVE identifiers, command flags and versions. Verify before acting, and use it only on systems you are authorized to work on.

🦉 Athena · EGen Labs

Downloads last month: -

GGUF

Model size

2B params

Architecture

lfm3

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for ErebusTN/Athena-GGUF

Base model

ErebusTN/Athena

Quantized

(1)

this model