Instructions to use Nitishsharma9/CyberNexus-14B-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 Nitishsharma9/CyberNexus-14B-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 Nitishsharma9/CyberNexus-14B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Nitishsharma9/CyberNexus-14B-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 Nitishsharma9/CyberNexus-14B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Nitishsharma9/CyberNexus-14B-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 Nitishsharma9/CyberNexus-14B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Nitishsharma9/CyberNexus-14B-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 Nitishsharma9/CyberNexus-14B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Nitishsharma9/CyberNexus-14B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Nitishsharma9/CyberNexus-14B-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use Nitishsharma9/CyberNexus-14B-GGUF with Ollama:
```
ollama run hf.co/Nitishsharma9/CyberNexus-14B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use Nitishsharma9/CyberNexus-14B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Nitishsharma9/CyberNexus-14B-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": "Nitishsharma9/CyberNexus-14B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Nitishsharma9/CyberNexus-14B-GGUF with Docker Model Runner:
```
docker model run hf.co/Nitishsharma9/CyberNexus-14B-GGUF:Q4_K_M
```

Lemonade

How to use Nitishsharma9/CyberNexus-14B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Nitishsharma9/CyberNexus-14B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.CyberNexus-14B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Nitishsharma9/CyberNexus-14B-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 Nitishsharma9/CyberNexus-14B-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 Nitishsharma9/CyberNexus-14B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Nitishsharma9/CyberNexus-14B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Nitishsharma9/CyberNexus-14B-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 "Nitishsharma9/CyberNexus-14B-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"

CyberNexus-14B-GGUF

GGUF quantizations of Qwen3.6-14B-A3B-FableVibes, a 14B MoE model fine-tuned on reasoning traces and strictly optimized for incredibly fast Python scripting, Fill-in-the-Middle (FIM) code completion, Ethical Hacking, and Cybersecurity operations.

Background

This model started as a highly capable base and was pruned down to ~14B active parameters, removing over half its expert capacity. A single QLoRA pass was then orchestrated entirely by an autonomous AI agent, utilizing ~4,600 raw reasoning traces from Claude Fable 5 to recover capabilities lost during pruning.

Rather than focusing strictly on agentic orchestration, this model serves as a general-purpose reasoning distill specifically tailored for offensive and defensive security contexts. The Fable CoT traces provide structured multi-step reasoning patterns from a frontier-class model, distilled into a footprint that can run on consumer hardware.

Core Capabilities:

⚡ Lightning Fast Python Scripting: Optimized to generate robust, production-ready Python tools in milliseconds.
🛡️ Ethical Hacking & Cyber Security: Deep knowledge of vulnerability assessment, penetration testing patterns, and defensive engineering.
🔄 Fill-in-the-Middle (FIM): Native support for seamless code completion right inside your IDE.

Hardware compatibility

Quantization	Bits	File Size (Est.)	RAM Required
`Q2_K`	2-bit	~5.32 GB	~7 GB
`Q3_K_M`	3-bit	~6.77 GB	~9 GB
`Q4_K_M`	4-bit	~8.47 GB	~10.5 GB
`Q5_K_M`	5-bit	~9.85 GB	~12 GB
`Q6_K`	6-bit	~11.3 GB	~13.5 GB
`Q8_0`	8-bit	~14.7 GB	~17 GB

Downloads last month: 296

GGUF

Model size

14B params

Architecture

qwen35moe

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

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