Instructions to use tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-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 tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF:Q2_K

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 tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF:Q2_K

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 tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF:Q2_K

Use Docker

docker model run hf.co/tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF:Q2_K

LM Studio
Jan

vLLM

How to use tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-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": "tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF:Q2_K

SGLang

How to use tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF with Ollama:
```
ollama run hf.co/tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF:Q2_K
```

Unsloth Studio

How to use tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF 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 tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF 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 tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF to start chatting

How to use tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF:Q2_K

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": "tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF:Q2_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF:Q2_K

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 "tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF:Q2_K" \
  --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 tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF with Docker Model Runner:
```
docker model run hf.co/tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF:Q2_K
```

Lemonade

How to use tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF:Q2_K

Run and chat with the model

lemonade run user.ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF-Q2_K

List all available models

lemonade list

Hermes Agent

How to use tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-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 tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF:Q2_K

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 tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF:Q2_K

Run Hermes

hermes

Atomic Chat

ServiceNow-AI/Apriel-Nemotron-15b-Thinker - GGUF

Join our Discord to learn more about what we're building ↗

This repo contains GGUF format model files for ServiceNow-AI/Apriel-Nemotron-15b-Thinker.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b5753.

Our projects

Forge

An OpenAI-compatible multi-provider routing layer.
🚀 Try it now! 🚀
Awesome MCP Servers	TensorBlock Studio

A comprehensive collection of Model Context Protocol (MCP) servers.	A lightweight, open, and extensible multi-LLM interaction studio.
👀 See what we built 👀	👀 See what we built 👀

Prompt template

<|system|>
You are a thoughtful and systematic AI assistant built by ServiceNow Language Models (SLAM) lab. Before providing an answer, analyze the problem carefully and present your reasoning step by step. After explaining your thought process, provide the final solution in the following format: [BEGIN FINAL RESPONSE] ... [END FINAL RESPONSE].

{system_prompt}
<|end|>
<|user|>
{prompt}
<|end|>
<|assistant|>
Here are my reasoning steps:

Model file specification

Filename	Quant type	File Size	Description
Apriel-Nemotron-15b-Thinker-Q2_K.gguf	Q2_K	5.794 GB	smallest, significant quality loss - not recommended for most purposes
Apriel-Nemotron-15b-Thinker-Q3_K_S.gguf	Q3_K_S	6.706 GB	very small, high quality loss
Apriel-Nemotron-15b-Thinker-Q3_K_M.gguf	Q3_K_M	7.396 GB	very small, high quality loss
Apriel-Nemotron-15b-Thinker-Q3_K_L.gguf	Q3_K_L	7.990 GB	small, substantial quality loss
Apriel-Nemotron-15b-Thinker-Q4_0.gguf	Q4_0	8.606 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Apriel-Nemotron-15b-Thinker-Q4_K_S.gguf	Q4_K_S	8.663 GB	small, greater quality loss
Apriel-Nemotron-15b-Thinker-Q4_K_M.gguf	Q4_K_M	9.113 GB	medium, balanced quality - recommended
Apriel-Nemotron-15b-Thinker-Q5_0.gguf	Q5_0	10.393 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Apriel-Nemotron-15b-Thinker-Q5_K_S.gguf	Q5_K_S	10.393 GB	large, low quality loss - recommended
Apriel-Nemotron-15b-Thinker-Q5_K_M.gguf	Q5_K_M	10.655 GB	large, very low quality loss - recommended
Apriel-Nemotron-15b-Thinker-Q6_K.gguf	Q6_K	12.293 GB	very large, extremely low quality loss
Apriel-Nemotron-15b-Thinker-Q8_0.gguf	Q8_0	15.919 GB	very large, extremely low quality loss - not recommended

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF --include "Apriel-Nemotron-15b-Thinker-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'

Downloads last month: 16

GGUF

Model size

15B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

Model tree for tensorblock/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF

Base model

ServiceNow-AI/Apriel-Nemotron-15b-Thinker

Quantized

(13)

this model