Instructions to use ibm-granite/granite-4.0-tiny-base-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ibm-granite/granite-4.0-tiny-base-preview with Transformers:

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

pipe = pipeline("text-generation", model="ibm-granite/granite-4.0-tiny-base-preview")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ibm-granite/granite-4.0-tiny-base-preview")
model = AutoModelForCausalLM.from_pretrained("ibm-granite/granite-4.0-tiny-base-preview")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ibm-granite/granite-4.0-tiny-base-preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ibm-granite/granite-4.0-tiny-base-preview"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ibm-granite/granite-4.0-tiny-base-preview",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ibm-granite/granite-4.0-tiny-base-preview

SGLang

How to use ibm-granite/granite-4.0-tiny-base-preview 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 "ibm-granite/granite-4.0-tiny-base-preview" \
    --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": "ibm-granite/granite-4.0-tiny-base-preview",
		"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 "ibm-granite/granite-4.0-tiny-base-preview" \
        --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": "ibm-granite/granite-4.0-tiny-base-preview",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ibm-granite/granite-4.0-tiny-base-preview with Docker Model Runner:
```
docker model run hf.co/ibm-granite/granite-4.0-tiny-base-preview
```

granite-4.0-tiny-base-preview

Commit History

Remove backup file and sign again

d74df31

Granite Preview commited on Nov 3, 2025

Update pip install instructions in README.md and signature

cfb630a

Granite Preview commited on Nov 3, 2025

Add MOT badge (#1)

36a44ba
verified

gabegoodhart

lehors commited on Nov 3, 2025

Add model signature and updated README explaining how to verify

c45bdd2

Granite.Preview commited on Jul 24, 2025

Update README.md

1745fd6
verified

rpand002 commited on May 6, 2025

Update README.md

ce3ec3f
verified

rpand002 commited on May 2, 2025

added transformer installation instructions.

87c0a89
verified

ranarag commited on May 2, 2025

Update README.md

871ea13
verified

rpand002 commited on May 1, 2025

Update README.md

d7f20d7
verified

rpand002 commited on May 1, 2025

Update README.md

6fb2b3b
verified

rpand002 commited on May 1, 2025

Update README.md

e927733
verified

rpand002 commited on May 1, 2025

add model card

688b292
verified

ranarag commited on May 1, 2025

changing max_position_embeddings

090f3e3
verified

ranarag commited on May 1, 2025

model upload

adf4329
verified

ranarag commited on May 1, 2025

initial commit

fb6cd73
verified

rpand002 commited on Apr 30, 2025

Commit History

Remove backup file and sign again d74df31

Update pip install instructions in README.md and signature cfb630a

Add MOT badge (#1) 36a44ba verified

Add model signature and updated README explaining how to verify c45bdd2

Update README.md 1745fd6 verified

Update README.md ce3ec3f verified

added transformer installation instructions. 87c0a89 verified

Update README.md 871ea13 verified

Update README.md d7f20d7 verified

Update README.md 6fb2b3b verified

Update README.md e927733 verified

add model card 688b292 verified

changing max_position_embeddings 090f3e3 verified

model upload adf4329 verified

initial commit fb6cd73 verified

Remove backup file and sign again

d74df31

Update pip install instructions in README.md and signature

cfb630a

Add MOT badge (#1)

36a44ba
verified

Add model signature and updated README explaining how to verify

c45bdd2

Update README.md

1745fd6
verified

Update README.md

ce3ec3f
verified

added transformer installation instructions.

87c0a89
verified

Update README.md

871ea13
verified

Update README.md

d7f20d7
verified

Update README.md

6fb2b3b
verified

Update README.md

e927733
verified

add model card

688b292
verified

changing max_position_embeddings

090f3e3
verified

model upload

adf4329
verified

initial commit

fb6cd73
verified