Instructions to use NbAiLab/borealis-270m-instruct-preview-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NbAiLab/borealis-270m-instruct-preview-gguf with Transformers:

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

pipe = pipeline("text-generation", model="NbAiLab/borealis-270m-instruct-preview-gguf")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("NbAiLab/borealis-270m-instruct-preview-gguf", dtype="auto")

llama-cpp-python

How to use NbAiLab/borealis-270m-instruct-preview-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="NbAiLab/borealis-270m-instruct-preview-gguf",
	filename="borealis-270m-instruct-preview-BF16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use NbAiLab/borealis-270m-instruct-preview-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf NbAiLab/borealis-270m-instruct-preview-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf NbAiLab/borealis-270m-instruct-preview-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf NbAiLab/borealis-270m-instruct-preview-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf NbAiLab/borealis-270m-instruct-preview-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 NbAiLab/borealis-270m-instruct-preview-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf NbAiLab/borealis-270m-instruct-preview-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 NbAiLab/borealis-270m-instruct-preview-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf NbAiLab/borealis-270m-instruct-preview-gguf:Q4_K_M

Use Docker

docker model run hf.co/NbAiLab/borealis-270m-instruct-preview-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use NbAiLab/borealis-270m-instruct-preview-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NbAiLab/borealis-270m-instruct-preview-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": "NbAiLab/borealis-270m-instruct-preview-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NbAiLab/borealis-270m-instruct-preview-gguf:Q4_K_M

SGLang

How to use NbAiLab/borealis-270m-instruct-preview-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 "NbAiLab/borealis-270m-instruct-preview-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": "NbAiLab/borealis-270m-instruct-preview-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 "NbAiLab/borealis-270m-instruct-preview-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": "NbAiLab/borealis-270m-instruct-preview-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use NbAiLab/borealis-270m-instruct-preview-gguf with Ollama:
```
ollama run hf.co/NbAiLab/borealis-270m-instruct-preview-gguf:Q4_K_M
```

Unsloth Studio new

How to use NbAiLab/borealis-270m-instruct-preview-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 NbAiLab/borealis-270m-instruct-preview-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 NbAiLab/borealis-270m-instruct-preview-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for NbAiLab/borealis-270m-instruct-preview-gguf to start chatting

Docker Model Runner
How to use NbAiLab/borealis-270m-instruct-preview-gguf with Docker Model Runner:
```
docker model run hf.co/NbAiLab/borealis-270m-instruct-preview-gguf:Q4_K_M
```

Lemonade

How to use NbAiLab/borealis-270m-instruct-preview-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull NbAiLab/borealis-270m-instruct-preview-gguf:Q4_K_M

Run and chat with the model

lemonade run user.borealis-270m-instruct-preview-gguf-Q4_K_M

List all available models

lemonade list

borealis-270m-instruct-preview

Model creator: NbAiLab
Original model: NbAiLab/borealis-270m-instruct-preview
GGUF quantization: provided by versae using llama.cpp

Available Quantizations

Q4_K_M
Q8_0
BF16

Special thanks

🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible.

Usage Examples

Q4_K_M

Ollama:

ollama run "hf.co/NbAiLab/borealis-270m-instruct-preview-gguf:Q4_K_M"

LM Studio:

lms load "NbAiLab/borealis-270m-instruct-preview-gguf/borealis-270m-instruct-preview-Q4_K_M.gguf"

llama.cpp CLI:

llama-cli --hf "NbAiLab/borealis-270m-instruct-preview-gguf:Q4_K_M" -p "The meaning to life and the universe is"

llama.cpp Server:

llama-server --hf "NbAiLab/borealis-270m-instruct-preview-gguf:Q4_K_M" -c 4096

Q8_0

Ollama:

ollama run "hf.co/NbAiLab/borealis-270m-instruct-preview-gguf:Q8_0"

LM Studio:

lms load "NbAiLab/borealis-270m-instruct-preview-gguf/borealis-270m-instruct-preview-Q8_0.gguf"

llama.cpp CLI:

llama-cli --hf "NbAiLab/borealis-270m-instruct-preview-gguf:Q8_0" -p "The meaning to life and the universe is"

llama.cpp Server:

llama-server --hf "NbAiLab/borealis-270m-instruct-preview-gguf:Q8_0" -c 4096

BF16

Ollama:

ollama run "hf.co/NbAiLab/borealis-270m-instruct-preview-gguf:BF16"

LM Studio:

lms load "NbAiLab/borealis-270m-instruct-preview-gguf/borealis-270m-instruct-preview-BF16.gguf"

llama.cpp CLI:

llama-cli --hf "NbAiLab/borealis-270m-instruct-preview-gguf:BF16" -p "The meaning to life and the universe is"

llama.cpp Server:

llama-server --hf "NbAiLab/borealis-270m-instruct-preview-gguf:BF16" -c 4096

Downloads last month: 34

GGUF

Model size

0.3B params

Architecture

gemma3

Hardware compatibility

4-bit

8-bit

16-bit

Model tree for NbAiLab/borealis-270m-instruct-preview-gguf

Base model

google/gemma-3-270m

Finetuned

google/gemma-3-270m-it

Finetuned

NbAiLab/borealis-270m-instruct-preview

Quantized

(3)

this model

Collection including NbAiLab/borealis-270m-instruct-preview-gguf

🌌 Borealis Preview

Collection

Preview release of the Borealis family of instruction tuned models by the National Library of Norway. • 20 items • Updated 2 days ago • 13