Instructions to use ibm-granite/granite-4.1-8b-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ibm-granite/granite-4.1-8b-base with Transformers:

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

pipe = pipeline("text-generation", model="ibm-granite/granite-4.1-8b-base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ibm-granite/granite-4.1-8b-base")
model = AutoModelForCausalLM.from_pretrained("ibm-granite/granite-4.1-8b-base")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ibm-granite/granite-4.1-8b-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ibm-granite/granite-4.1-8b-base"
# 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-4.1-8b-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ibm-granite/granite-4.1-8b-base

SGLang

How to use ibm-granite/granite-4.1-8b-base 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-4.1-8b-base" \
    --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-4.1-8b-base",
		"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-4.1-8b-base" \
        --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-4.1-8b-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ibm-granite/granite-4.1-8b-base with Docker Model Runner:
```
docker model run hf.co/ibm-granite/granite-4.1-8b-base
```

Provenance questions

by MichielBuisman - opened 8 days ago

Discussion

MichielBuisman

8 days ago

•

edited 8 days ago

@yousafshah congrats on this massive achievement! Could you provide some more clarity regarding to provenance? Which model served as LLM-as-Judge in the SFT pipeline, and does the ISO 42001 certification from Granite 4.0 extend to 4.1?

yousafshah

IBM Granite org 7 days ago

Thanks @MichielBuisman We used gpt-oss-120b as judge. The ISO 42001 certification covers the Granite AI Management System (AIMS) for our flagship Granite language models. As part of the audit, our policies, tooling, documentation, logs, resourcing, and controls are reviewed by both an internal and external auditor. To maintain compliance, IBM undergoes annual recertification audits. Our ISO 42001 recertification audit for 2026 is actually kicking off in the coming weeks. You do not need to undergo a new audit every time a new Granite language model comes out. This is just covered as part of the regularly scheduled, annual recertification process.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment