Instructions to use google/gemma-2b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use google/gemma-2b with Transformers:

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

pipe = pipeline("text-generation", model="google/gemma-2b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-2b")

llama-cpp-python

How to use google/gemma-2b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="google/gemma-2b",
	filename="gemma-2b.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Inference
Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use google/gemma-2b with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf google/gemma-2b
# Run inference directly in the terminal:
llama-cli -hf google/gemma-2b

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf google/gemma-2b
# Run inference directly in the terminal:
llama-cli -hf google/gemma-2b

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 google/gemma-2b
# Run inference directly in the terminal:
./llama-cli -hf google/gemma-2b

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 google/gemma-2b
# Run inference directly in the terminal:
./build/bin/llama-cli -hf google/gemma-2b

Use Docker

docker model run hf.co/google/gemma-2b

LM Studio
Jan

vLLM

How to use google/gemma-2b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "google/gemma-2b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "google/gemma-2b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/google/gemma-2b

SGLang

How to use google/gemma-2b 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 "google/gemma-2b" \
    --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": "google/gemma-2b",
		"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 "google/gemma-2b" \
        --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": "google/gemma-2b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use google/gemma-2b with Ollama:
```
ollama run hf.co/google/gemma-2b
```

Unsloth Studio new

How to use google/gemma-2b 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 google/gemma-2b 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 google/gemma-2b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for google/gemma-2b to start chatting

Docker Model Runner
How to use google/gemma-2b with Docker Model Runner:
```
docker model run hf.co/google/gemma-2b
```

Lemonade

How to use google/gemma-2b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull google/gemma-2b

Run and chat with the model

lemonade run user.gemma-2b-{{QUANT_TAG}}

List all available models

lemonade list

New discussion

Resources

View closed (36)

Update README.md

#91 opened 23 days ago by

ceoavinash

Get Access

#90 opened 6 months ago by

AurasZ

Request: Get Access

#89 opened 6 months ago by

AurasZ

provide me acess of this directory to use this model

#88 opened 7 months ago by

Aman5678

Request: request for access

#87 opened 9 months ago by

Deepak4667

deploy

#86 opened 10 months ago by

xiaogao33

https://huggingface.co/k0vv/kov

#85 opened 10 months ago by

k0vv

Request: DOI

#84 opened 10 months ago by

Turning123

Request: DOI

#83 opened 11 months ago by

Arefin994

Update config.json

#82 opened 11 months ago by

ArchaveCommunity

Used gemma-2b in my Pre Proposal work for Google Summer Of Code 2025

#81 opened about 1 year ago by

Kakaarot

Problems with running on CPU

#79 opened over 1 year ago by

IExist999

Gated Repos Permission

#78 opened over 1 year ago by

aymenmir

google/gemma-2b-kamba-instruct

#77 opened over 1 year ago by

Qybera

Update README.md

#75 opened over 1 year ago by

LCG123

Request: DOI

#74 opened over 1 year ago by

Jonasbukhave

Interview request: genAI evaluation & documentation

#73 opened over 1 year ago by

meggymuggy

Supported Languages

#72 opened over 1 year ago by

vpkprasanna

Upload config (3).json

#70 opened over 1 year ago by

Malekhmem

Randomness of the output of the trained model

#68 opened almost 2 years ago by

Sam1989

Can't reproduce hellaswag result - getting 42.3% v.s. 71.4 % reported

#67 opened almost 2 years ago by

robgarct

gemma 2b

#65 opened almost 2 years ago by

powei59

Any one who use the script in the Model Card for inference purpose?

#64 opened almost 2 years ago by

disper84

huhuhuhus

#63 opened almost 2 years ago by

huhuhuhus

403 Forbidden: Authorization error

#62 opened almost 2 years ago by

parkerbotta

Memory requirements to load the model

#61 opened almost 2 years ago by

nroshania

Following blog for fine tuning gemma-2b doesn't yield same results

#60 opened almost 2 years ago by

chongdashu

[AUTOMATED] Model Memory Requirements

#59 opened about 2 years ago by

model-sizer-bot

[AUTOMATED] Model Memory Requirements

#58 opened about 2 years ago by

model-sizer-bot

[AUTOMATED] Model Memory Requirements

#57 opened about 2 years ago by

model-sizer-bot

[AUTOMATED] Model Memory Requirements

#56 opened about 2 years ago by

model-sizer-bot

[AUTOMATED] Model Memory Requirements

#55 opened about 2 years ago by

model-sizer-bot

Running finetuned inference on CPU - accelerate ImportError

#54 opened about 2 years ago by

saikrishna6491

Unable to reproduce the score of gemma_2b at pass@1 in humaneval.

#53 opened about 2 years ago by

ChiYuqi

Feature extraction suitability?

#52 opened about 2 years ago by

ivoras

Update README.md

#51 opened about 2 years ago by

raj729

gemma 2b inference Endpoints error

#46 opened about 2 years ago by

gawon16

gemma -2b with multi-gpu

#44 opened about 2 years ago by

Iamexperimenting

pretraining Gemma for domain dataset

➕ 1

#41 opened about 2 years ago by

Iamexperimenting

[AUTOMATED] Model Memory Requirements

#40 opened about 2 years ago by

model-sizer-bot

Gemma tokenizer issue

#37 opened about 2 years ago by

Akshayextreme

Question about their name.. why it is 2b???

#36 opened about 2 years ago by

sh0416

[AUTOMATED] Model Memory Requirements

#35 opened about 2 years ago by

model-sizer-bot

[AUTOMATED] Model Memory Requirements

#34 opened about 2 years ago by

model-sizer-bot

What is the context size for Gemma? I get error when asking for it in the config file e.g., AttributeError("'GemmaConfig' object has no attribute 'context_length'")

#32 opened about 2 years ago by

brando

torch import required in examples

#31 opened about 2 years ago by

shamikbose89

ImportError: Using `bitsandbytes` 8-bit quantization requires Accelerate: `pip install accelerate` and the latest version of bitsandbytes

#29 opened about 2 years ago by

WQW

torch.cuda.OutOfMemoryError

#26 opened about 2 years ago by

shiwanglai

GPU utlisation high on Gemma-2b-it

#24 opened about 2 years ago by

sharad07

Sentiment analysis

#23 opened about 2 years ago by

PTsag