Instructions to use evalengine/decision-0.8b-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 evalengine/decision-0.8b-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 evalengine/decision-0.8b-gguf:F16
# Run inference directly in the terminal:
llama cli -hf evalengine/decision-0.8b-gguf:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf evalengine/decision-0.8b-gguf:F16
# Run inference directly in the terminal:
llama cli -hf evalengine/decision-0.8b-gguf:F16

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 evalengine/decision-0.8b-gguf:F16
# Run inference directly in the terminal:
./llama-cli -hf evalengine/decision-0.8b-gguf:F16

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 evalengine/decision-0.8b-gguf:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf evalengine/decision-0.8b-gguf:F16

Use Docker

docker model run hf.co/evalengine/decision-0.8b-gguf:F16

LM Studio
Jan
Ollama
How to use evalengine/decision-0.8b-gguf with Ollama:
```
ollama run hf.co/evalengine/decision-0.8b-gguf:F16
```
Unsloth Desktop

How to use evalengine/decision-0.8b-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf evalengine/decision-0.8b-gguf:F16

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": "evalengine/decision-0.8b-gguf:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use evalengine/decision-0.8b-gguf with Docker Model Runner:
```
docker model run hf.co/evalengine/decision-0.8b-gguf:F16
```

Lemonade

How to use evalengine/decision-0.8b-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull evalengine/decision-0.8b-gguf:F16

Run and chat with the model

lemonade run user.decision-0.8b-gguf-F16

List all available models

lemonade list

Hermes Agent

How to use evalengine/decision-0.8b-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 evalengine/decision-0.8b-gguf:F16

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 evalengine/decision-0.8b-gguf:F16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use evalengine/decision-0.8b-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf evalengine/decision-0.8b-gguf:F16

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 "evalengine/decision-0.8b-gguf:F16" \
  --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"

decision-0.8b-gguf

File size: 978 Bytes

ce99379

model,display_name,cases,family_mean_accuracy,all_case_accuracy,errors
hosted_jev,Jev 1.13 · hosted TypeSafe,2800,0.7894444444444444,0.7760714285714285,0
expanded,Decision-4B (ours),2800,0.763888888888889,0.7914285714285715,0
djev,"Djev · NVFP4, one step",2800,0.7611111111111111,0.7571428571428571,0
baseline,Local Tev-style baseline · 4B,2800,0.6797222222222222,0.6903571428571429,0
decision_08b,Decision-0.8B (ours),2800,0.6261111111111111,0.6882142857142857,0
published_tev,Published Tev · 4B,2800,0.6183333333333333,0.6496428571428572,0
kev,Kev-4B · installed revision,2800,0.6122222222222222,0.6475,0
laya,Laya · English root,2800,0.5833333333333334,0.6425,0
flock,FLock this-that 1.1,2800,0.5627777777777778,0.6128571428571429,0
qwen,Original Qwen3.5-4B,2800,0.5186111111111111,0.5832142857142857,0
tev_08b,Published Tev · 0.8B,2800,0.5141666666666667,0.5553571428571429,0
qwen_08b,Original Qwen3.5-0.8B,2800,0.39805555555555555,0.43892857142857145,0