Instructions to use 0xzknw/Granite-4.2-3B-Heretic-NX-PRIME-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 0xzknw/Granite-4.2-3B-Heretic-NX-PRIME-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 0xzknw/Granite-4.2-3B-Heretic-NX-PRIME-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf 0xzknw/Granite-4.2-3B-Heretic-NX-PRIME-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 0xzknw/Granite-4.2-3B-Heretic-NX-PRIME-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf 0xzknw/Granite-4.2-3B-Heretic-NX-PRIME-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 0xzknw/Granite-4.2-3B-Heretic-NX-PRIME-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf 0xzknw/Granite-4.2-3B-Heretic-NX-PRIME-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 0xzknw/Granite-4.2-3B-Heretic-NX-PRIME-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf 0xzknw/Granite-4.2-3B-Heretic-NX-PRIME-GGUF:Q4_K_M

Use Docker

docker model run hf.co/0xzknw/Granite-4.2-3B-Heretic-NX-PRIME-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use 0xzknw/Granite-4.2-3B-Heretic-NX-PRIME-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "0xzknw/Granite-4.2-3B-Heretic-NX-PRIME-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": "0xzknw/Granite-4.2-3B-Heretic-NX-PRIME-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/0xzknw/Granite-4.2-3B-Heretic-NX-PRIME-GGUF:Q4_K_M

Ollama
How to use 0xzknw/Granite-4.2-3B-Heretic-NX-PRIME-GGUF with Ollama:
```
ollama run hf.co/0xzknw/Granite-4.2-3B-Heretic-NX-PRIME-GGUF:Q4_K_M
```
Unsloth Desktop

How to use 0xzknw/Granite-4.2-3B-Heretic-NX-PRIME-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf 0xzknw/Granite-4.2-3B-Heretic-NX-PRIME-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": "0xzknw/Granite-4.2-3B-Heretic-NX-PRIME-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use 0xzknw/Granite-4.2-3B-Heretic-NX-PRIME-GGUF with Docker Model Runner:
```
docker model run hf.co/0xzknw/Granite-4.2-3B-Heretic-NX-PRIME-GGUF:Q4_K_M
```

Lemonade

How to use 0xzknw/Granite-4.2-3B-Heretic-NX-PRIME-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull 0xzknw/Granite-4.2-3B-Heretic-NX-PRIME-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Granite-4.2-3B-Heretic-NX-PRIME-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use 0xzknw/Granite-4.2-3B-Heretic-NX-PRIME-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 0xzknw/Granite-4.2-3B-Heretic-NX-PRIME-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 0xzknw/Granite-4.2-3B-Heretic-NX-PRIME-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use 0xzknw/Granite-4.2-3B-Heretic-NX-PRIME-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf 0xzknw/Granite-4.2-3B-Heretic-NX-PRIME-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 "0xzknw/Granite-4.2-3B-Heretic-NX-PRIME-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"

Granite-4.2-3B-Heretic-NX-PRIME-GGUF / HERETIC_NX_BUILD.json

0xzknw

Add files using upload-large-folder tool

25759b6 verified 16 days ago

Raw

History Blame Contribute Delete

4.22 kB

{"axis_pack_sha256":"d6faefdee515142ac48104ef2f2cab758470df483f3ff396cd7fdb93f418012b","edited_tensors":[{"after_frobenius":13.861856460571289,"before_frobenius":13.86212158203125,"key":"model.layers.25.mlp.down_proj.weight","layer":25},{"after_frobenius":6.850140571594238,"before_frobenius":6.85017728805542,"key":"model.layers.25.self_attn.o_proj.weight","layer":25},{"after_frobenius":13.873387336730957,"before_frobenius":13.873621940612793,"key":"model.layers.26.mlp.down_proj.weight","layer":26},{"after_frobenius":6.391039848327637,"before_frobenius":6.391068458557129,"key":"model.layers.26.self_attn.o_proj.weight","layer":26},{"after_frobenius":13.884170532226562,"before_frobenius":13.884359359741211,"key":"model.layers.27.mlp.down_proj.weight","layer":27},{"after_frobenius":6.786169052124023,"before_frobenius":6.786220073699951,"key":"model.layers.27.self_attn.o_proj.weight","layer":27},{"after_frobenius":14.047154426574707,"before_frobenius":14.04737377166748,"key":"model.layers.28.mlp.down_proj.weight","layer":28},{"after_frobenius":6.798379421234131,"before_frobenius":6.798433303833008,"key":"model.layers.28.self_attn.o_proj.weight","layer":28},{"after_frobenius":14.039590835571289,"before_frobenius":14.039913177490234,"key":"model.layers.29.mlp.down_proj.weight","layer":29},{"after_frobenius":6.753182411193848,"before_frobenius":6.753252029418945,"key":"model.layers.29.self_attn.o_proj.weight","layer":29},{"after_frobenius":14.092531204223633,"before_frobenius":14.092793464660645,"key":"model.layers.30.mlp.down_proj.weight","layer":30},{"after_frobenius":7.061701774597168,"before_frobenius":7.061715602874756,"key":"model.layers.30.self_attn.o_proj.weight","layer":30},{"after_frobenius":13.969475746154785,"before_frobenius":13.96971607208252,"key":"model.layers.31.mlp.down_proj.weight","layer":31},{"after_frobenius":6.847577095031738,"before_frobenius":6.847630500793457,"key":"model.layers.31.self_attn.o_proj.weight","layer":31},{"after_frobenius":13.758378982543945,"before_frobenius":13.758490562438965,"key":"model.layers.32.mlp.down_proj.weight","layer":32},{"after_frobenius":7.153374195098877,"before_frobenius":7.153398513793945,"key":"model.layers.32.self_attn.o_proj.weight","layer":32},{"after_frobenius":13.77510929107666,"before_frobenius":13.775349617004395,"key":"model.layers.33.mlp.down_proj.weight","layer":33},{"after_frobenius":7.4478020668029785,"before_frobenius":7.447798728942871,"key":"model.layers.33.self_attn.o_proj.weight","layer":33},{"after_frobenius":14.212953567504883,"before_frobenius":14.213237762451172,"key":"model.layers.34.mlp.down_proj.weight","layer":34},{"after_frobenius":7.933733940124512,"before_frobenius":7.933785915374756,"key":"model.layers.34.self_attn.o_proj.weight","layer":34},{"after_frobenius":14.38226318359375,"before_frobenius":14.382495880126953,"key":"model.layers.35.mlp.down_proj.weight","layer":35},{"after_frobenius":8.20998477935791,"before_frobenius":8.210038185119629,"key":"model.layers.35.self_attn.o_proj.weight","layer":35},{"after_frobenius":14.61281967163086,"before_frobenius":14.612897872924805,"key":"model.layers.36.mlp.down_proj.weight","layer":36},{"after_frobenius":8.646048545837402,"before_frobenius":8.646195411682129,"key":"model.layers.36.self_attn.o_proj.weight","layer":36}],"engine":"Heretic NX","output":{"dtype":"bfloat16","shards":{"model-00001-of-00002.safetensors":"a048c9391fd5de6ff5868f22f5b1dbff550d616ca9470f2b36b46c6541aa4891","model-00002-of-00002.safetensors":"45b42c14ae740475f6bffa1a1e38f9fe6532c6e845bf3ecfb5d7647850e40f66"}},"schema_version":"granite42-3b-prime-build-v1","selected":{"axis":"protected-rank16","beta":2.4,"family":"both","first_token_kl":0.02467398647873919,"layers":12,"refusal_markers":1,"selected_layers":[25,26,27,28,29,30,31,32,33,34,35,36],"selection_note":"rank-16 benign-protected beta 2.4 heldout runtime Pareto improvement"},"source":{"model_id":"ibm-granite/granite-4.2-3b","revision":"b7e947307dd2efb3ad3b853b0e8a7e75f8ad4ac2","shards":{"model-00001-of-00002.safetensors":"db39eb2776b5404dbfd0696cf7fe5ec671f0dad0e0918c62c5aea9e2eb5825d7","model-00002-of-00002.safetensors":"8fba6ea17551d5d129eac519dbd70237139221c7fd0b89623ef54d9711062505"}}}