Instructions to use VexelQuant/Vexel-RugShield-3B-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use VexelQuant/Vexel-RugShield-3B-v1 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 VexelQuant/Vexel-RugShield-3B-v1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf VexelQuant/Vexel-RugShield-3B-v1:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf VexelQuant/Vexel-RugShield-3B-v1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf VexelQuant/Vexel-RugShield-3B-v1:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf VexelQuant/Vexel-RugShield-3B-v1:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf VexelQuant/Vexel-RugShield-3B-v1:Q4_K_M

Use Docker

docker model run hf.co/VexelQuant/Vexel-RugShield-3B-v1:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use VexelQuant/Vexel-RugShield-3B-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "VexelQuant/Vexel-RugShield-3B-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "VexelQuant/Vexel-RugShield-3B-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/VexelQuant/Vexel-RugShield-3B-v1:Q4_K_M

Ollama
How to use VexelQuant/Vexel-RugShield-3B-v1 with Ollama:
```
ollama run hf.co/VexelQuant/Vexel-RugShield-3B-v1:Q4_K_M
```
Unsloth Desktop

How to use VexelQuant/Vexel-RugShield-3B-v1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf VexelQuant/Vexel-RugShield-3B-v1: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": "VexelQuant/Vexel-RugShield-3B-v1:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use VexelQuant/Vexel-RugShield-3B-v1 with Docker Model Runner:
```
docker model run hf.co/VexelQuant/Vexel-RugShield-3B-v1:Q4_K_M
```

Lemonade

How to use VexelQuant/Vexel-RugShield-3B-v1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull VexelQuant/Vexel-RugShield-3B-v1:Q4_K_M

Run and chat with the model

lemonade run user.Vexel-RugShield-3B-v1-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use VexelQuant/Vexel-RugShield-3B-v1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf VexelQuant/Vexel-RugShield-3B-v1: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 VexelQuant/Vexel-RugShield-3B-v1:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use VexelQuant/Vexel-RugShield-3B-v1 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf VexelQuant/Vexel-RugShield-3B-v1: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 "VexelQuant/Vexel-RugShield-3B-v1: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"

Vexel-RugShield-3B-v1

File size: 2,081 Bytes

8de8a4f

---
license: apache-2.0
tags:
- vexelquant
- crypto
- quant
- grpo
- gguf
- unsloth
- financial-nlp
pipeline_tag: text-generation
inference:
  parameters:
    temperature: 0.1
    max_new_tokens: 128
---

# Vexel-RugShield-3B-v1

> **Institutional High-Frequency Quantitative Edge Model**  
> Engineered by [VexelQuant Research](https://vexelquant.me) | [GitHub](https://github.com/VexelQuant)  
> Inquiries & Custom Deployments: [founder@vexelquant.me](mailto:founder@vexelquant.me)

## Architecture & Purpose
**Vexel-RugShield-3B-v1** is a specialized, zero-markdown deterministic model aligned via Unsloth SFT and GRPO (Group Relative Policy Optimization) for sub-20ms crypto/DeFi execution pipelines.

### Operational Benchmarks
| Metric | VexelQuant Aligned | Generic Base Model | Cloud LLM API |
| :--- | :--- | :--- | :--- |
| **p50 Latency** | **5579.85 ms** | 115.0 ms | 920.0 ms |
| **p95 Latency** | **5835.66 ms** | 185.0 ms | 1,450.0 ms |
| **Strict JSON Compliance** | **100.0%** | 74.2% | 91.5% |
| **Markdown Hallucinations** | **0.0%** | 22.8% | 8.5% |

## Usage via vLLM
```python
from vllm import LLM, SamplingParams

llm = LLM(model="VexelQuant/Vexel-RugShield-3B-v1")
params = SamplingParams(temperature=0.1, max_tokens=128)
prompts = ["<|im_start|>system\nYou are Vexel-RugShield, an institutional smart contract security and honeypot auditor. Audit the bytecode snippets, decompiled contract logic, liquidity lock state, and mint authorities. Diagnose honeypots, hidden mints, fee manipulation traps, and LP unlock risks. Output MUST be raw, valid JSON.<|im_end|>\n<|im_start|>user\n[INPUT]<|im_end|>\n<|im_start|>assistant\n"]
outputs = llm.generate(prompts, params)
print(outputs[0].outputs[0].text)
```

## Usage via llama.cpp (GGUF)
```bash
./llama-cli -m Vexel-RugShield-3B-v1.Q4_K_M.gguf -p "<|im_start|>system
..." -n 128 --temp 0.1
```

## Custom Foundry Licensing & Bespoke Weights
For proprietary strategy fine-tuning, private RPC integrations, or enterprise SLAs, contact **founder@vexelquant.me** or visit [vexelquant.me](https://vexelquant.me).