Instructions to use cognis-digital/Opal-8B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cognis-digital/Opal-8B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="cognis-digital/Opal-8B-GGUF",
	filename="opal-8b-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use cognis-digital/Opal-8B-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 cognis-digital/Opal-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf cognis-digital/Opal-8B-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 cognis-digital/Opal-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf cognis-digital/Opal-8B-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 cognis-digital/Opal-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf cognis-digital/Opal-8B-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 cognis-digital/Opal-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf cognis-digital/Opal-8B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/cognis-digital/Opal-8B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use cognis-digital/Opal-8B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cognis-digital/Opal-8B-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": "cognis-digital/Opal-8B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cognis-digital/Opal-8B-GGUF:Q4_K_M

Ollama
How to use cognis-digital/Opal-8B-GGUF with Ollama:
```
ollama run hf.co/cognis-digital/Opal-8B-GGUF:Q4_K_M
```

Unsloth Studio

How to use cognis-digital/Opal-8B-GGUF 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 cognis-digital/Opal-8B-GGUF 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 cognis-digital/Opal-8B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for cognis-digital/Opal-8B-GGUF to start chatting

How to use cognis-digital/Opal-8B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf cognis-digital/Opal-8B-GGUF: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": "cognis-digital/Opal-8B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use cognis-digital/Opal-8B-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 cognis-digital/Opal-8B-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 cognis-digital/Opal-8B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use cognis-digital/Opal-8B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf cognis-digital/Opal-8B-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 "cognis-digital/Opal-8B-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"

Docker Model Runner
How to use cognis-digital/Opal-8B-GGUF with Docker Model Runner:
```
docker model run hf.co/cognis-digital/Opal-8B-GGUF:Q4_K_M
```

Lemonade

How to use cognis-digital/Opal-8B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cognis-digital/Opal-8B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Opal-8B-GGUF-Q4_K_M

List all available models

lemonade list

Opal-8B — a security-specialized Llama-3.1-8B that beats the stock model

Opal-8B is stock Llama-3.1-8B-Instruct with defensive-security expertise trained in via LoRA — so it keeps the base model's general ability and adds a large security edge on top. On our harness it beats stock Llama-3.1-8B-Instruct overall, wins on math and security, and matches it on code.

Built by Cognis Digital (US). Native Llama-3.1 tool-calling. Part of the Opal suite with the Opal router.

Why this works (and the merges didn't)

We first tried merging open models (DARE-TIES). Every merge lost to stock Instruct — a merge only interpolates its components, it can't exceed them, and the grafts degraded the base's code/math. The fix was to stop merging and train: a LoRA on frozen stock Instruct, on a defensive-security corpus generated by open teacher models (gpt-oss-20b, Phi-4). Training adds capability; merging only averages it. That is the entire difference between the table below and a loss.

Benchmarks (measured here — Ollama, greedy, n = 25 subset, identical harness)

code = HumanEval pass@1 (executed); math = GSM8K exact-match; sec = a transparent defensive-security keyword rubric (bench/tasks/sec.json: Cobalt Strike detection, SQLi, MCP threat-modeling, Sigma, UEFI bootkit). blend = 0.45·code + 0.25·math + 0.30·sec.

model	code	math	sec	blend
Opal-8B (Q4_K_M)	0.88	0.76	0.424	0.713
Llama-3.1-8B-Instruct (stock peer)	0.92	0.68	0.212	0.648

Opal wins the blend (0.713 vs 0.648), wins math and security, and is within noise on code. Honest note: stock Instruct is marginally ahead on raw HumanEval (0.92 vs 0.88) — we publish that, not hide it. Every number reproduces with the harness in this repo.

Published frontier reference (official full-set numbers, different harness, context only — an 8B is not a frontier model):

model	HumanEval	GSM8K	source
Llama-3.1-8B-Instruct	72.6	84.5	Meta official evals
GPT-4o	90.2	~96	public reports
Claude 3.5 Sonnet	92.0	96.4	Anthropic

HumanEval/GSM8K are saturated at the frontier and no longer reported head-to-head; shown only to place the 8B class. No frontier-parity claim.

Quantization ladder

file	size	use
`opal-8b-Q4_K_M.gguf`	4.9 GB	default — best size/quality
`opal-8b-Q5_K_M.gguf`	5.7 GB	higher quality
`opal-8b-Q6_K.gguf`	6.6 GB	near-lossless
`opal-8b-Q8_0.gguf`	8.5 GB	maximum fidelity

Native tool-calling (Ollama)

import ollama
ollama.chat(model="opal-8b", messages=[{"role":"user","content":"weather in Charleston?"}],
            tools=[{"type":"function","function":{"name":"get_weather",
              "parameters":{"type":"object","properties":{"location":{"type":"string"}},
              "required":["location"]}}}])

What it's for

Detection engineering (Sigma/Suricata), threat modeling, MCP/agent security, firmware/ICS reasoning, secure code review, agentic tool use — with general code/reasoning at Llama-3.1-8B-Instruct level.

How it was made

Base: Llama-3.1-8B-Instruct (frozen). LoRA (r=16) trained locally on CPU (no cloud) over a defensive-security SFT corpus distilled from gpt-oss-20b + Phi-4, then merged and quantized. Recipe and harness are in the repo.

Limitations & safety

Inherits Llama-3.1-Instruct's alignment and knowledge cutoff. Security content is for authorized, defensive use (detection, threat modeling, hardening). Verify generated code before running it.

License

Apache-2.0. Trainer/quantizer: PEFT + llama.cpp.

Downloads last month: 193

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

4-bit

5-bit

Model tree for cognis-digital/Opal-8B-GGUF

Base model

meta-llama/Llama-3.1-8B

Finetuned

meta-llama/Llama-3.1-8B-Instruct

Adapter

(2573)

this model