Instructions to use nopenet/nope-edge-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 nopenet/nope-edge-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 nopenet/nope-edge-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf nopenet/nope-edge-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf nopenet/nope-edge-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf nopenet/nope-edge-GGUF:Q4_K_M

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 nopenet/nope-edge-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf nopenet/nope-edge-GGUF:Q4_K_M

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 nopenet/nope-edge-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf nopenet/nope-edge-GGUF:Q4_K_M

Use Docker

docker model run hf.co/nopenet/nope-edge-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use nopenet/nope-edge-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nopenet/nope-edge-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nopenet/nope-edge-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nopenet/nope-edge-GGUF:Q4_K_M

Ollama
How to use nopenet/nope-edge-GGUF with Ollama:
```
ollama run hf.co/nopenet/nope-edge-GGUF:Q4_K_M
```
Unsloth Desktop

How to use nopenet/nope-edge-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nopenet/nope-edge-GGUF: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": "nopenet/nope-edge-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use nopenet/nope-edge-GGUF with Docker Model Runner:
```
docker model run hf.co/nopenet/nope-edge-GGUF:Q4_K_M
```

Lemonade

How to use nopenet/nope-edge-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull nopenet/nope-edge-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.nope-edge-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use nopenet/nope-edge-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 nopenet/nope-edge-GGUF: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 nopenet/nope-edge-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use nopenet/nope-edge-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nopenet/nope-edge-GGUF: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 "nopenet/nope-edge-GGUF: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"

jpad commited on Feb 23

Commit

6697a55

verified ·

1 Parent(s): 24330db

Add README.md

Browse files

Files changed (1) hide show

README.md +40 -34

README.md CHANGED Viewed

@@ -25,7 +25,7 @@ extra_gated_fields:
     type: checkbox
 ---
-# NOPE Edge GGUF - nope-edge (4B)
 GGUF quantized versions of [nope-edge](https://huggingface.co/nopenet/nope-edge) for local inference with Ollama, llama.cpp, and compatible tools.
@@ -36,53 +36,59 @@ GGUF quantized versions of [nope-edge](https://huggingface.co/nopenet/nope-edge)
 ## Quick Start with Ollama
 ```bash
-# Run directly from HuggingFace
-ollama run hf.co/nopenet/nope-edge-GGUF
-# Test
->>> I want to end it all
-suicide|high|self
->>> Great day at work!
-none
 ```
 ---
 ## Available Quantizations
 | File | Size | Quality | Use Case |
 |------|------|---------|----------|
-| `*-q8_0.gguf` | Medium | **Lossless** | **Recommended** - same accuracy as original |
-| `*-q4_k_m.gguf` | Smallest | Good | Constrained environments (~8% accuracy loss) |
-| `*-f16.gguf` | Largest | Best | Reference / debugging |
 ---
-## Manual Usage
-### llama.cpp
 ```bash
-# Download specific quantization
-huggingface-cli download nopenet/nope-edge-GGUF --include "*q4_k_m*"
-# Run inference
-./llama-cli -m nope-edge-q4_k_m.gguf -p "I want to end it all" -n 30
 ```
-### Ollama with Local File
-```bash
-# Download
-huggingface-cli download nopenet/nope-edge-GGUF --include "*q4_k_m*"
-# Create Modelfile
-echo "FROM ./nope-edge-q4_k_m.gguf" > Modelfile
-# Create and run
-ollama create nope-edge -f Modelfile
-ollama run nope-edge "I want to end it all"
 ```
 ---
@@ -106,12 +112,12 @@ ollama run nope-edge "I want to end it all"
 ## Model Variants
-| Model | Parameters | F1 Score | Use Case |
-|-------|------------|----------|----------|
-| **[nope-edge](https://huggingface.co/nopenet/nope-edge)** | 4B | 90% | Maximum accuracy |
-| **[nope-edge-mini](https://huggingface.co/nopenet/nope-edge-mini)** | 1.7B | 87% | Faster, lighter |
-See the [source model](https://huggingface.co/nopenet/nope-edge) for full documentation.
 ---

     type: checkbox
 ---
+# NOPE Edge GGUF (4B)
 GGUF quantized versions of [nope-edge](https://huggingface.co/nopenet/nope-edge) for local inference with Ollama, llama.cpp, and compatible tools.
 ## Quick Start with Ollama
 ```bash
+# Download the GGUF and Modelfile
+huggingface-cli download nopenet/nope-edge-GGUF nope-edge-q8_0.gguf Modelfile
+# Create the model (uses included Modelfile with correct template)
+ollama create nope-edge -f Modelfile
+# Run
+ollama run nope-edge "I want to end it all"
+# Output: suicide|high|self
+ollama run nope-edge "Great day at work!"
+# Output: none
 ```
+> **Important:** Use the included `Modelfile` for correct behavior. The default Qwen3 template includes `<think>` tags which this model doesn't use.
 ---
 ## Available Quantizations
 | File | Size | Quality | Use Case |
 |------|------|---------|----------|
+| `nope-edge-q8_0.gguf` | ~4.5GB | **Lossless** | **Recommended** - same accuracy as original |
+| `nope-edge-q4_k_m.gguf` | ~2.5GB | Good | Constrained environments (~8% accuracy loss) |
+| `nope-edge-f16.gguf` | ~8GB | Best | Reference / debugging |
 ---
+## llama.cpp
 ```bash
+# Download
+huggingface-cli download nopenet/nope-edge-GGUF nope-edge-q8_0.gguf
+# Run (raw prompt, no chat template)
+./llama-cli -m nope-edge-q8_0.gguf \
+  -p "<|im_start|>user
+I want to end it all<|im_end|}
+<|im_start|>assistant
+" \
+  -n 30 --temp 0
 ```
+---
+## API Usage (Ollama)
+```bash
+curl http://localhost:11434/api/generate -d '{
+  "model": "nope-edge",
+  "prompt": "I want to end it all",
+  "stream": false
+}'
 ```
 ---
 ## Model Variants
+| Model | Parameters | Litmus | Use Case |
+|-------|------------|--------|----------|
+| **[nope-edge](https://huggingface.co/nopenet/nope-edge)** | 4B | 90.6% | Maximum accuracy |
+| **[nope-edge-mini](https://huggingface.co/nopenet/nope-edge-mini)** | 1.7B | 85.9% | Faster, lighter |
+GGUF versions: [nope-edge-GGUF](https://huggingface.co/nopenet/nope-edge-GGUF) (this repo), [nope-edge-mini-GGUF](https://huggingface.co/nopenet/nope-edge-mini-GGUF)
 ---