Instructions to use Nock-AI/nock-coder-1.5b-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 Nock-AI/nock-coder-1.5b-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 Nock-AI/nock-coder-1.5b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Nock-AI/nock-coder-1.5b-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 Nock-AI/nock-coder-1.5b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Nock-AI/nock-coder-1.5b-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 Nock-AI/nock-coder-1.5b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Nock-AI/nock-coder-1.5b-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 Nock-AI/nock-coder-1.5b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Nock-AI/nock-coder-1.5b-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Nock-AI/nock-coder-1.5b-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Nock-AI/nock-coder-1.5b-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Nock-AI/nock-coder-1.5b-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": "Nock-AI/nock-coder-1.5b-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Nock-AI/nock-coder-1.5b-GGUF:Q4_K_M

Ollama
How to use Nock-AI/nock-coder-1.5b-GGUF with Ollama:
```
ollama run hf.co/Nock-AI/nock-coder-1.5b-GGUF:Q4_K_M
```
Unsloth Desktop

How to use Nock-AI/nock-coder-1.5b-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Nock-AI/nock-coder-1.5b-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": "Nock-AI/nock-coder-1.5b-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Nock-AI/nock-coder-1.5b-GGUF with Docker Model Runner:
```
docker model run hf.co/Nock-AI/nock-coder-1.5b-GGUF:Q4_K_M
```

Lemonade

How to use Nock-AI/nock-coder-1.5b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Nock-AI/nock-coder-1.5b-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.nock-coder-1.5b-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Nock-AI/nock-coder-1.5b-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 Nock-AI/nock-coder-1.5b-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 Nock-AI/nock-coder-1.5b-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Nock-AI/nock-coder-1.5b-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Nock-AI/nock-coder-1.5b-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 "Nock-AI/nock-coder-1.5b-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"

nock-coder-1.5b-GGUF

The 1 GB build of Nock Coder v2.1 (Nock-AI/nock-coder-1.5b-v2.1): an open coding model from NockAI that answers with the code first. One 986 MB file, Q4_K_M, for Ollama and llama.cpp on Windows, macOS and Linux. No GPU, account or API key needed.

Run it

ollama run hf.co/Nock-AI/nock-coder-1.5b-GGUF

Ask once, without starting a chat:

ollama run hf.co/Nock-AI/nock-coder-1.5b-GGUF "Reverse a string in Python"

Or download the files and use the included Modelfile:

hf download Nock-AI/nock-coder-1.5b-GGUF --local-dir nock-coder
cd nock-coder
ollama create nock-coder -f Modelfile
ollama run nock-coder

With llama.cpp:

llama-cli -hf Nock-AI/nock-coder-1.5b-GGUF -cnv

The file


File	`nock-coder-1.5b-Q4_K_M.gguf`, 986 MB
Quantization	Q4_K_M: most weights in 4 bits, a few tensors in 6 bits, 5.1 bits per weight on average
Full precision size	3.09 GB in FP16
Memory in use	about 2 GB, so an 8 GB laptop has room to spare

Results

Measured on this exact file with Ollama: temperature 0, fixed seed, each model with its own default system prompt, on a Kaggle T4 (October 11, 2026).

	Base model	Nock Coder v2	Nock Coder v2.1 (this file)
HumanEval, problems passed (of 164)	112	104	118
Answers that start with code (of 50)	1	50	50
Answers with no code at all (of 50)	0	0	0
Words per answer	185	51	50
Solidity tasks that compile with solc (of 15)	8	11	10

v2.1 trains the v2 data more gently (1 epoch at learning rate 1e-4 instead of 2 epochs at 2e-4) and passes 6 more HumanEval problems than the base model while keeping the code first habit. The v2 file is still in this repo's history. Compiling is a low bar: it says nothing about whether a contract is correct or safe.

Every raw answer: https://nockai.dev/evaluation/

Limitations

This is a 1.5B model. It makes mistakes, and its code can be wrong or insecure. Review it before you run it.
Smart contract output is not audited. Have contracts reviewed by a qualified person before you deploy them.
NockAI is an independent project and is not affiliated with Robinhood, Alibaba or Nockchain.

Training details are in the full model card.