Instructions to use unsloth/Llama-3.2-3B-unsloth-bnb-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/Llama-3.2-3B-unsloth-bnb-4bit with Transformers:

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

pipe = pipeline("text-generation", model="unsloth/Llama-3.2-3B-unsloth-bnb-4bit")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("unsloth/Llama-3.2-3B-unsloth-bnb-4bit")
model = AutoModelForCausalLM.from_pretrained("unsloth/Llama-3.2-3B-unsloth-bnb-4bit")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use unsloth/Llama-3.2-3B-unsloth-bnb-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/Llama-3.2-3B-unsloth-bnb-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/Llama-3.2-3B-unsloth-bnb-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/unsloth/Llama-3.2-3B-unsloth-bnb-4bit

SGLang

How to use unsloth/Llama-3.2-3B-unsloth-bnb-4bit 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 "unsloth/Llama-3.2-3B-unsloth-bnb-4bit" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/Llama-3.2-3B-unsloth-bnb-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "unsloth/Llama-3.2-3B-unsloth-bnb-4bit" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/Llama-3.2-3B-unsloth-bnb-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio

How to use unsloth/Llama-3.2-3B-unsloth-bnb-4bit 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 unsloth/Llama-3.2-3B-unsloth-bnb-4bit 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 unsloth/Llama-3.2-3B-unsloth-bnb-4bit to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for unsloth/Llama-3.2-3B-unsloth-bnb-4bit to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="unsloth/Llama-3.2-3B-unsloth-bnb-4bit",
    max_seq_length=2048,
)

Docker Model Runner
How to use unsloth/Llama-3.2-3B-unsloth-bnb-4bit with Docker Model Runner:
```
docker model run hf.co/unsloth/Llama-3.2-3B-unsloth-bnb-4bit
```

shimmyshimmer commited on Jan 24, 2025

Commit

72af128

verified ·

1 Parent(s): 1c242e6

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -12,8 +12,9 @@ tags:
 - unsloth
 - transformers
 ---
 ## ***See [our collection](https://huggingface.co/collections/unsloth/llama-32-66f46afde4ca573864321a22) for all versions of Llama 3.2 including GGUF, 4-bit and original 16-bit formats.***
 # Finetune Llama 3.2, Gemma 2, Mistral 2-5x faster with 70% less memory via Unsloth!

 - unsloth
 - transformers
 ---
 ## ***See [our collection](https://huggingface.co/collections/unsloth/llama-32-66f46afde4ca573864321a22) for all versions of Llama 3.2 including GGUF, 4-bit and original 16-bit formats.***
+*Unsloth's [Dynamic 4-bit Quants](https://unsloth.ai/blog/dynamic-4bit) selectively avoids quantizing certain parameters, greatly increase accuracy than standard 4-bit.<br>See our full collection of Unsloth quants on [Hugging Face here.](https://huggingface.co/collections/unsloth/unsloth-4-bit-dynamic-quants-67503bb873f89e15276c44e7)*
+<br>
 # Finetune Llama 3.2, Gemma 2, Mistral 2-5x faster with 70% less memory via Unsloth!