Instructions to use unsloth/gemma-3-12b-pt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/gemma-3-12b-pt with Transformers:

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

pipe = pipeline("image-text-to-text", model="unsloth/gemma-3-12b-pt")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("unsloth/gemma-3-12b-pt")
model = AutoModelForImageTextToText.from_pretrained("unsloth/gemma-3-12b-pt")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use unsloth/gemma-3-12b-pt with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/gemma-3-12b-pt"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/gemma-3-12b-pt",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/unsloth/gemma-3-12b-pt

SGLang

How to use unsloth/gemma-3-12b-pt 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/gemma-3-12b-pt" \
    --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/gemma-3-12b-pt",
		"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/gemma-3-12b-pt" \
        --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/gemma-3-12b-pt",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio new

How to use unsloth/gemma-3-12b-pt 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/gemma-3-12b-pt 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/gemma-3-12b-pt to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for unsloth/gemma-3-12b-pt to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="unsloth/gemma-3-12b-pt",
    max_seq_length=2048,
)

Docker Model Runner
How to use unsloth/gemma-3-12b-pt with Docker Model Runner:
```
docker model run hf.co/unsloth/gemma-3-12b-pt
```

shimmyshimmer commited on Mar 12, 2025

Commit

a9792ee

verified ·

1 Parent(s): e5a6395

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -16,7 +16,7 @@ tags:
     <strong>See <a href="https://huggingface.co/collections/unsloth/gemma-3-67d12b7e8816ec6efa7e4e5b">our collection</a> for all versions of Gemma 3 including GGUF, 4-bit & 16-bit formats.</strong>
   </p>
   <p style="margin-bottom: 0;">
-    <em>Unsloth's Gemma 3 <a href="https://unsloth.ai/blog/dynamic-4bit">Dynamic Quants</a> is selectively quantized, greatly improving accuracy over standard 4-bit.</em>
   </p>
   <div style="display: flex; gap: 5px; align-items: center; ">
     <a href="https://github.com/unslothai/unsloth/">
@@ -32,14 +32,14 @@ tags:
 <h1 style="margin-top: 0rem;">✨ Fine-tune Gemma 3 with Unsloth!</h1>
 </div>
-- Fine-tune Gemma 3 (12B) for free using our Google [Colab notebook here](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Gemma3.ipynb)!
 - Read our Blog about Gemma 3 support: [unsloth.ai/blog/gemma3](https://unsloth.ai/blog/gemma3)
 - View the rest of our notebooks in our [docs here](https://docs.unsloth.ai/get-started/unsloth-notebooks).
 - Export your fine-tuned model to GGUF, Ollama, llama.cpp or 🤗HF.
 | Unsloth supports          |    Free Notebooks                                                                                           | Performance | Memory use |
 |-----------------|--------------------------------------------------------------------------------------------------------------------------|-------------|----------|
-| **GRPO with Gemma 3 (12B)**      | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Gemma_3_(12B)-GRPO.ipynb)               | 2x faster | 80% less |
 | **Llama-3.2 (3B)**      | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.2_(1B_and_3B)-Conversational.ipynb)               | 2.4x faster | 58% less |
 | **Llama-3.2 (11B vision)**      | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.2_(11B)-Vision.ipynb)               | 2x faster | 60% less |
 | **Qwen2.5 (7B)**      | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Qwen2.5_(7B)-Alpaca.ipynb)               | 2x faster | 60% less |

     <strong>See <a href="https://huggingface.co/collections/unsloth/gemma-3-67d12b7e8816ec6efa7e4e5b">our collection</a> for all versions of Gemma 3 including GGUF, 4-bit & 16-bit formats.</strong>
   </p>
   <p style="margin-bottom: 0;">
+    <em><a href="https://docs.unsloth.ai/basics/tutorial-how-to-run-gemma-3-effectively">Read our Guide</a> to see how to Run Gemma 3 correctly.</em>
   </p>
   <div style="display: flex; gap: 5px; align-items: center; ">
     <a href="https://github.com/unslothai/unsloth/">
 <h1 style="margin-top: 0rem;">✨ Fine-tune Gemma 3 with Unsloth!</h1>
 </div>
+- Fine-tune Gemma 3 (12B) for free using our Google [Colab notebook here](https://docs.unsloth.ai/get-started/unsloth-notebooks)!
 - Read our Blog about Gemma 3 support: [unsloth.ai/blog/gemma3](https://unsloth.ai/blog/gemma3)
 - View the rest of our notebooks in our [docs here](https://docs.unsloth.ai/get-started/unsloth-notebooks).
 - Export your fine-tuned model to GGUF, Ollama, llama.cpp or 🤗HF.
 | Unsloth supports          |    Free Notebooks                                                                                           | Performance | Memory use |
 |-----------------|--------------------------------------------------------------------------------------------------------------------------|-------------|----------|
+| **GRPO with Gemma 3 (12B)**      | [▶️ Start on Colab](https://docs.unsloth.ai/get-started/unsloth-notebooks)               | 2x faster | 80% less |
 | **Llama-3.2 (3B)**      | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.2_(1B_and_3B)-Conversational.ipynb)               | 2.4x faster | 58% less |
 | **Llama-3.2 (11B vision)**      | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.2_(11B)-Vision.ipynb)               | 2x faster | 60% less |
 | **Qwen2.5 (7B)**      | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Qwen2.5_(7B)-Alpaca.ipynb)               | 2x faster | 60% less |