Instructions to use ma77145/decider-0.8b-Q8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use ma77145/decider-0.8b-Q8 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 ma77145/decider-0.8b-Q8
# Run inference directly in the terminal:
llama cli -hf ma77145/decider-0.8b-Q8

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ma77145/decider-0.8b-Q8
# Run inference directly in the terminal:
llama cli -hf ma77145/decider-0.8b-Q8

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 ma77145/decider-0.8b-Q8
# Run inference directly in the terminal:
./llama-cli -hf ma77145/decider-0.8b-Q8

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 ma77145/decider-0.8b-Q8
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ma77145/decider-0.8b-Q8

Use Docker

docker model run hf.co/ma77145/decider-0.8b-Q8

LM Studio
Jan
Ollama
How to use ma77145/decider-0.8b-Q8 with Ollama:
```
ollama run hf.co/ma77145/decider-0.8b-Q8
```
Unsloth Desktop

How to use ma77145/decider-0.8b-Q8 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ma77145/decider-0.8b-Q8

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": "ma77145/decider-0.8b-Q8"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ma77145/decider-0.8b-Q8 with Docker Model Runner:
```
docker model run hf.co/ma77145/decider-0.8b-Q8
```

Lemonade

How to use ma77145/decider-0.8b-Q8 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ma77145/decider-0.8b-Q8

Run and chat with the model

lemonade run user.decider-0.8b-Q8-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use ma77145/decider-0.8b-Q8 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ma77145/decider-0.8b-Q8

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 ma77145/decider-0.8b-Q8

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ma77145/decider-0.8b-Q8 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ma77145/decider-0.8b-Q8

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 "ma77145/decider-0.8b-Q8" \
  --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"

decider-0.8b Q8_0 GGUF (community conversion)

Quantized GGUF of Mapika/decider-0.8b (Apache-2.0), the smallest typed-decision ("System One") model: one forward pass returns calibrated Choice / Score / noul answers over caller-defined options. Converted with llama.cpp convert_hf_to_gguf.py + llama-quantize q8_0. No official 0.8b GGUF exists — this fills that gap.

Measured (GTX 1050 Ti 4GB, Vulkan, llama.cpp)

JevBench hard-public 111 (letter-readout harness): acc 0.405
Fitted temperature T=5.55 (NLL 1.62→1.12, ECE 0.33→0.13)
Toy routing battery 5/5, ~0.7s total, 920MB resident

Use

llama-server -m decider-0.8b-q8.gguf -c 8192 --device Vulkan1 -ngl 99
curl localhost:8080/completion -H 'Content-Type: application/json' -d '{
  "prompt": "Context: My card was charged twice.\n\nQuestion: Which team?\nOptions:\n(A) billing: charges, refunds\n(B) technical: bugs\nAnswer: (",
  "temperature": 0, "n_predict": 1, "n_probs": 10}'

Single-letter answers; divide log-probs by 5.55 and softmax for calibrated confidence.