Instructions to use GYETI/Prism-4B-Reasoning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use GYETI/Prism-4B-Reasoning 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 GYETI/Prism-4B-Reasoning:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf GYETI/Prism-4B-Reasoning:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf GYETI/Prism-4B-Reasoning:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf GYETI/Prism-4B-Reasoning: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 GYETI/Prism-4B-Reasoning:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf GYETI/Prism-4B-Reasoning: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 GYETI/Prism-4B-Reasoning:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf GYETI/Prism-4B-Reasoning:Q4_K_M

Use Docker

docker model run hf.co/GYETI/Prism-4B-Reasoning:Q4_K_M

LM Studio
Jan

vLLM

How to use GYETI/Prism-4B-Reasoning with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GYETI/Prism-4B-Reasoning"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GYETI/Prism-4B-Reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/GYETI/Prism-4B-Reasoning:Q4_K_M

Ollama
How to use GYETI/Prism-4B-Reasoning with Ollama:
```
ollama run hf.co/GYETI/Prism-4B-Reasoning:Q4_K_M
```

Unsloth Studio

How to use GYETI/Prism-4B-Reasoning with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for GYETI/Prism-4B-Reasoning to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for GYETI/Prism-4B-Reasoning to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for GYETI/Prism-4B-Reasoning to start chatting

How to use GYETI/Prism-4B-Reasoning with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GYETI/Prism-4B-Reasoning:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "GYETI/Prism-4B-Reasoning:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use GYETI/Prism-4B-Reasoning with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GYETI/Prism-4B-Reasoning: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 GYETI/Prism-4B-Reasoning:Q4_K_M

Run Hermes

hermes

OpenClaw new

How to use GYETI/Prism-4B-Reasoning with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GYETI/Prism-4B-Reasoning: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 "GYETI/Prism-4B-Reasoning: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"

Docker Model Runner
How to use GYETI/Prism-4B-Reasoning with Docker Model Runner:
```
docker model run hf.co/GYETI/Prism-4B-Reasoning:Q4_K_M
```

Lemonade

How to use GYETI/Prism-4B-Reasoning with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull GYETI/Prism-4B-Reasoning:Q4_K_M

Run and chat with the model

lemonade run user.Prism-4B-Reasoning-Q4_K_M

List all available models

lemonade list

Atomic Chat

⚖️ Attribution & Licensing

Prism-4B-Reasoning is a derivative work fine-tuned from the pre-trained Nemotron 3 base architecture created by NVIDIA.

This model is distributed openly under the terms of the Apache 2.0 License. In accordance with license guidelines, this model contains extensive weight alterations from the original framework to adopt a new custom identity and functional task profile.

The original work and licensing elements can be audited via the Nvidia Nemotron Repository.

Downloads last month: -

GGUF

Model size

4B params

Architecture

nemotron_h

Hardware compatibility

4-bit

Model tree for GYETI/Prism-4B-Reasoning

Unable to build the model tree, the base model loops to the model itself. Learn more.