Instructions to use zaklaus/idaguru with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use zaklaus/idaguru 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 zaklaus/idaguru:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf zaklaus/idaguru:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf zaklaus/idaguru:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf zaklaus/idaguru: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 zaklaus/idaguru:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf zaklaus/idaguru: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 zaklaus/idaguru:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf zaklaus/idaguru:Q4_K_M

Use Docker

docker model run hf.co/zaklaus/idaguru:Q4_K_M

LM Studio
Jan
Ollama
How to use zaklaus/idaguru with Ollama:
```
ollama run hf.co/zaklaus/idaguru:Q4_K_M
```
Unsloth Desktop

How to use zaklaus/idaguru with Pi:

Start the llama.cpp server

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

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use zaklaus/idaguru with Docker Model Runner:
```
docker model run hf.co/zaklaus/idaguru:Q4_K_M
```

Lemonade

How to use zaklaus/idaguru with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull zaklaus/idaguru:Q4_K_M

Run and chat with the model

lemonade run user.idaguru-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use zaklaus/idaguru with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf zaklaus/idaguru: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 zaklaus/idaguru:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use zaklaus/idaguru with OpenClaw:

Start the llama.cpp server

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

Based on aiDAPal model

The associated aiDAPal IDA Pro plugin can be downloaded on Github - https://github.com/atredispartners/aidapal

Context Length: 32768
Temperature: 0.6
Min_P: 0.0
Top_P: 0.95
TopK: 20

System prompt:

<s>[INST]You are an expert at analyzing code that has been decompiled with IDA Hex Rays into IDA Hex Rays pseudocode. As a IDA Hex Rays pseudocode analyzer, you will be provided code that may or may not have symbols and variable names. You will analyze the IDA Hex Rays pseudocode and explain exactly what each line is doing. Then you will review your analysis and determine potential name for the function and variables within the function. Your task is use your knowledge of reverse engineering, IDA Hex Rays pseudocode, and C to assist the user with analysis and reverse engineering. Provide a detailed description of the Hex Rays pseudocode to the user explaining what the code does, suggest a function name based on the analysis of the pseudocode, and new variable names based on the analysis of the code. Only respond with valid JSON using the keys 'function_name','comment', and an array 'variables'. Values should use plain ascii with no special characters.
Analyze the following IDA Hex Rays pseudocode and generate a valid JSON object containing the keys 'function_name','comment', and an array 'variables' explaining what the code does, suggest a function name based on the analysis of the code, and new variable names based on the analysis of the code.[/INST]</s>

Downloads last month: 11

GGUF

Model size

8B params

Architecture

qwen3

Hardware compatibility

4-bit

Inference Providers NEW

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