Instructions to use startlux-models/StartLux-Decision-4B-Q8_0-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 startlux-models/StartLux-Decision-4B-Q8_0-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 startlux-models/StartLux-Decision-4B-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf startlux-models/StartLux-Decision-4B-Q8_0-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf startlux-models/StartLux-Decision-4B-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf startlux-models/StartLux-Decision-4B-Q8_0-GGUF:Q8_0

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 startlux-models/StartLux-Decision-4B-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf startlux-models/StartLux-Decision-4B-Q8_0-GGUF:Q8_0

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 startlux-models/StartLux-Decision-4B-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf startlux-models/StartLux-Decision-4B-Q8_0-GGUF:Q8_0

Use Docker

docker model run hf.co/startlux-models/StartLux-Decision-4B-Q8_0-GGUF:Q8_0

LM Studio
Jan
Ollama
How to use startlux-models/StartLux-Decision-4B-Q8_0-GGUF with Ollama:
```
ollama run hf.co/startlux-models/StartLux-Decision-4B-Q8_0-GGUF:Q8_0
```
Unsloth Desktop

How to use startlux-models/StartLux-Decision-4B-Q8_0-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf startlux-models/StartLux-Decision-4B-Q8_0-GGUF:Q8_0

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": "startlux-models/StartLux-Decision-4B-Q8_0-GGUF:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use startlux-models/StartLux-Decision-4B-Q8_0-GGUF with Docker Model Runner:
```
docker model run hf.co/startlux-models/StartLux-Decision-4B-Q8_0-GGUF:Q8_0
```

Lemonade

How to use startlux-models/StartLux-Decision-4B-Q8_0-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull startlux-models/StartLux-Decision-4B-Q8_0-GGUF:Q8_0

Run and chat with the model

lemonade run user.StartLux-Decision-4B-Q8_0-GGUF-Q8_0

List all available models

lemonade list

Hermes Agent

How to use startlux-models/StartLux-Decision-4B-Q8_0-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 startlux-models/StartLux-Decision-4B-Q8_0-GGUF:Q8_0

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 startlux-models/StartLux-Decision-4B-Q8_0-GGUF:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use startlux-models/StartLux-Decision-4B-Q8_0-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf startlux-models/StartLux-Decision-4B-Q8_0-GGUF:Q8_0

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 "startlux-models/StartLux-Decision-4B-Q8_0-GGUF:Q8_0" \
  --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"

StartLux-Decision-4B-Q8_0-GGUF

StartLux-Decision-4B in Q8_0 (8-bit) as a GGUF file for llama.cpp. The decision server in this repository turns it into the same typed decisions, with a probability for every option, as the original model.

Precisions

Repository	Bits	Size	Same decision as the original	JevBench public, of 231
StartLux-Decision-4B-Q8_0-GGUF (this repository)	8-bit	4.48 GB	100.0%	204 (88.3%)	recommended
StartLux-Decision-4B-Q4_K_M-GGUF	4-bit	2.71 GB	98.3%	201 (87.0%)	smallest
StartLux-Decision-4B-BF16-GGUF	16-bit	8.42 GB	100.0%	204 (88.3%)	the original weights, unchanged
StartLux-Decision-4B (original weights)				204 (88.3%)	for comparison

"Same decision" is the share of the 231 public JevBench items on which the file picks the same answer as the original weights run through the startlux_decision package, with the same prompts, readout and temperatures. Q8_0 and Q4_K_M are llama.cpp's standard quantizations of BF16, without an importance matrix.

Download and run

hf download startlux-models/StartLux-Decision-4B-Q8_0-GGUF --local-dir StartLux-Decision-4B-Q8_0-GGUF
cd StartLux-Decision-4B-Q8_0-GGUF
pip install -r requirements.txt                     # transformers and torch; a CPU build of torch is enough

# llama.cpp serves the weights; the decision server puts the prompt format, readout and calibration on top
llama-server -m StartLux-Decision-4B-Q8_0.gguf -ngl 99 -c 16384 --parallel 4 --port 8081 &
python -m startlux_decision.gguf_server --model-dir . --llama http://127.0.0.1:8081 --port 8090

-ngl 99 puts every layer on the GPU (CUDA or Metal); leave it out on a CPU-only machine. llama.cpp has to be recent enough for this model (build b10454 or newer).

Requests and responses use the TypeSafe /v1/systemone format:

curl -s localhost:8090/v1/systemone -H 'Content-Type: application/json' -d '{
  "state": {"ticket": "I was charged twice for order #4411 and the app still shows it as unpaid."},
  "questions": {
    "team":   {"type": "choice", "instructions": "Which team should handle this ticket?",
               "criteria": {"billing": "Payments, refunds and invoices",
                            "shipping": "Delivery and tracking",
                            "technical": "App, login and account problems"}},
    "urgent": {"type": "noul", "instructions": "Should this ticket be answered today?"}
  }
}'

Plain chat with a GGUF file does not give these decisions: the option-letter readout and the per-type temperatures live in gguf_server.py, not in the weights. The file holds the text decoder only.

License

The model weights are released under CC BY-NC 4.0: free for research and other non-commercial use, with attribution. Commercial use requires a separate license from StartLux Labs; contact contact@startlux.com. The inference code in startlux_decision/ is Apache-2.0. See LICENSE and NOTICE.

Downloads last month: 3,581

GGUF

Model size

4B params

Architecture

qwen35

Hardware compatibility

8-bit

Inference Providers NEW

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

Model tree for startlux-models/StartLux-Decision-4B-Q8_0-GGUF

Base model

startlux-models/StartLux-Decision-4B

Quantized

(4)

this model

Space using startlux-models/StartLux-Decision-4B-Q8_0-GGUF 1

Collection including startlux-models/StartLux-Decision-4B-Q8_0-GGUF

StartLux-Decision

Collection

Typed decision models from 0.8B to 27B. Every question comes back with a probability for each option. • 21 items • Updated 4 days ago • 7