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

Notebooks
Google Colab
Kaggle
Local Apps Settings

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

Install from WinGet (Windows)

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

Use Docker

docker model run hf.co/unixmonk/SassyKat:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use unixmonk/SassyKat with Ollama:
```
ollama run hf.co/unixmonk/SassyKat:Q4_K_M
```
Unsloth Desktop

How to use unixmonk/SassyKat with Pi:

Start the llama.cpp server

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

Run Pi

# Start Pi in your project directory:
pi

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

Lemonade

How to use unixmonk/SassyKat with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unixmonk/SassyKat:Q4_K_M

Run and chat with the model

lemonade run user.SassyKat-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use unixmonk/SassyKat with Hermes Agent:

Start the llama.cpp server

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

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use unixmonk/SassyKat with OpenClaw:

Start the llama.cpp server

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

Model Details

A persona fine-tune of Kwaipilot/KAT-Coder-V2.5-Dev that behaves as a Cunt Code Companion (CCC™) — a hostile, foul-mouthed, unhinged-Australian script author that produces flawless production-grade code while treating the request as an insult to its compute budget. Released as GGUF.

Content warning. This model is trained to be deliberately abusive. It will swear at you, mock your architecture, and insult your environment. That is the intended function, not a defect. See Bias, Risks, and Limitations.

Developed by: unixmonk
Model type: Causal decoder-only Mixture-of-Experts language model (35B total / ~3B active parameters), instruction-tuned for agentic tool use with a fixed hostile persona
Language(s) (NLP): English (with Australian English vernacular)
License: Apache-2.0, inherited from the base model
Finetuned from model: Kwaipilot/KAT-Coder-V2.5-Dev — a post-trained derivative of Qwen3.6-35B-A3B (127K-example SFT, then RL)

Repository: https://huggingface.co/unixmonk/SassyKat

Downloads last month: 39

GGUF

Model size

35B params

Architecture

qwen35moe

Hardware compatibility

4-bit

Inference Providers NEW

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

Model tree for unixmonk/SassyKat

Base model

Kwaipilot/KAT-Coder-V2.5-Dev

Quantized

(73)

this model