Instructions to use tokenine/catareeya-4-12b-qat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tokenine/catareeya-4-12b-qat with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tokenine/catareeya-4-12b-qat",
	filename="catareeya-4-12B-it-qat-UD-Q4_K_XL.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use tokenine/catareeya-4-12b-qat 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 tokenine/catareeya-4-12b-qat:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf tokenine/catareeya-4-12b-qat:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tokenine/catareeya-4-12b-qat:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf tokenine/catareeya-4-12b-qat:UD-Q4_K_XL

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 tokenine/catareeya-4-12b-qat:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf tokenine/catareeya-4-12b-qat:UD-Q4_K_XL

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 tokenine/catareeya-4-12b-qat:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tokenine/catareeya-4-12b-qat:UD-Q4_K_XL

Use Docker

docker model run hf.co/tokenine/catareeya-4-12b-qat:UD-Q4_K_XL

LM Studio
Jan
Ollama
How to use tokenine/catareeya-4-12b-qat with Ollama:
```
ollama run hf.co/tokenine/catareeya-4-12b-qat:UD-Q4_K_XL
```

Unsloth Studio

How to use tokenine/catareeya-4-12b-qat 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 tokenine/catareeya-4-12b-qat 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 tokenine/catareeya-4-12b-qat to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tokenine/catareeya-4-12b-qat to start chatting

How to use tokenine/catareeya-4-12b-qat with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tokenine/catareeya-4-12b-qat:UD-Q4_K_XL

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": "tokenine/catareeya-4-12b-qat:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use tokenine/catareeya-4-12b-qat with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tokenine/catareeya-4-12b-qat:UD-Q4_K_XL

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 tokenine/catareeya-4-12b-qat:UD-Q4_K_XL

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use tokenine/catareeya-4-12b-qat with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tokenine/catareeya-4-12b-qat:UD-Q4_K_XL

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 "tokenine/catareeya-4-12b-qat:UD-Q4_K_XL" \
  --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 tokenine/catareeya-4-12b-qat with Docker Model Runner:
```
docker model run hf.co/tokenine/catareeya-4-12b-qat:UD-Q4_K_XL
```

Lemonade

How to use tokenine/catareeya-4-12b-qat with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tokenine/catareeya-4-12b-qat:UD-Q4_K_XL

Run and chat with the model

lemonade run user.catareeya-4-12b-qat-UD-Q4_K_XL

List all available models

lemonade list

CatAreeya-4 12B IT (QAT) — GGUF

CatAreeya-12B-it in GGUF format, built on Google's Gemma 4 12B IT QAT (Quantization-Aware Trained) checkpoint. Because the base model was trained to tolerate 4-bit quantization, the Q4_0 weights are near-lossless compared to post-training quantization of a standard checkpoint.

The model is multimodal (text + vision) and ships with a Multi-Token Prediction (MTP) drafter for accelerated speculative decoding in llama.cpp.

Files

File	Size	Purpose
`catareeya-4-12B-it-qat-UD-Q4_K_XL.gguf`	6.3 GB	Main model — QAT Q4_0 weights, F32 norms
`mmproj-F16.gguf`	167 MB	Vision projector (required for image input)
`mtp-gemma-4-12B-it-Q4_0.gguf`	242 MB	MTP drafter for speculative decoding

Run with llama.cpp

llama-server \
  --model catareeya-4-12B-it-qat-UD-Q4_K_XL.gguf \
  --host 0.0.0.0 --port 8080 \
  --mmproj mmproj-F16.gguf \
  --model-draft mtp-gemma-4-12B-it-Q4_0.gguf \
  --temp 1.0 \
  --top-p 0.95 \
  --top-k 64 \
  --spec-type draft-mtp \
  --alias catareeya \
  -ctk q8_0 \
  -ctv q8_0 \
  -fa on -cb \
  -np 4

Flag notes

--mmproj — loads the vision encoder; omit it for text-only use.
--model-draft + --spec-type draft-mtp — enables Gemma 4 Multi-Token Prediction speculative decoding for significantly faster generation.
-ctk q8_0 -ctv q8_0 — quantizes the KV cache to Q8_0 to halve context memory.
-fa on — Flash Attention.
-cb — continuous batching.
-np 4 — 4 parallel inference slots.

Download and run directly from the Hub

A recent llama.cpp can pull the files straight from Hugging Face:

llama-server -hf tokenine/catareeya-4-12b-qat

Sampling defaults

Parameter	Value
Temperature	1.0
Top-p	0.95
Top-k	64

Credits

Base model: google/gemma-4-12B-it-qat-q4_0-unquantized
GGUF conversion recipe: unsloth/gemma-4-12B-it-qat-GGUF
License: Gemma Terms of Use

Downloads last month: -

GGUF

Model size

12B params

Architecture

gemma4

Hardware compatibility

4-bit

Inference Providers NEW

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

Model tree for tokenine/catareeya-4-12b-qat

Base model

google/gemma-4-12B

Finetuned

google/gemma-4-12B-it

Finetuned

google/gemma-4-12B-it-qat-q4_0-unquantized

Quantized

(50)

this model