ibm-granite/granite-4.2-language-models

ibm-granite/granite-4.2-language-models

License: Apache-2.0

Stars: 8

Forks: 1

Open issues: 1

Created: 2026-08-23T16:27:49Z

Pushed: 2026-08-25T21:01:25Z

Default branch: main

Fork: no

Archived: no

README:

:hugs: HuggingFace Collection&nbsp | :hugs: HuggingFace Technical Blog | :speech_balloon: Discussions Page&nbsp

---

Overview

Granite is a family of open-source large language models developed by IBM, designed for enterprise and research use. Granite models are built to be versatile, safe, and efficient — covering a range of sizes and capabilities from compact edge-deployable models to large-scale reasoning systems.

The Granite 4.2 generation introduces native reasoning (thinking) capabilities, allowing models to perform step-by-step chain-of-thought reasoning before producing final answers. This significantly improves performance on complex math, coding, multi-step logic, and agentic tool-calling tasks. The Granite 4.2 familiy features dense decoder-only architectures in three sizes — 3B, 8B, and 30B, with quantized variants per model size.

The Granite 4.2 dense models are post-trained on top of Granite 4.1 base models. Please refer to the Granite 4.1 blog for details on the pre-training phase. We provide instruct models checkpoints fine-tuned for dialogue, instruction following, helpfulness, safety, and reasoning, as well as quantized variants for each model size.

All models are publicly released under the Apache 2.0 license, allowing free use for both research and commercial purposes. The data curation and training processes were specifically designed for enterprise scenarios and customization, incorporating governance, risk, and compliance (GRC) evaluations alongside IBM's standard data clearance and document quality review procedures.

How to Use our Models?

To use any of our models, pick an appropriate model_path from: 1. ibm-granite/granite-4.2-3b 2. ibm-granite/granite-4.2-8b 3. ibm-granite/granite-4.2-30b

Quick Start Inference Examples with Transformers

Installation

pip install torch torchvision torchaudio
pip install accelerate transformers

Inference (Thinking Mode)

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = "ibm-granite/granite-4.2-30b"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, device_map="cuda", torch_dtype=torch.bfloat16)
model.eval()

messages = [
{"role": "user", "content": "How many r's are in the word 'strawberry'?"},
]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, enable_thinking=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)

with torch.no_grad():
output = model.generate(**inputs, max_new_tokens=8192, temperature=1.0, top_p=0.95, do_sample=True)

print(tokenizer.decode(output[0][inputs.input_ids.shape[-1]:], skip_special_tokens=False))

Example Output

Okay, let's see. The problem is to find how many 'r's are in the word 'strawberry'.

First, I need to write out the word: s t r a w b e r r y.

Now, I need to count the number of 'r' letters. Let's list each letter and check for 'r'.

1. s – not r
2. t – not r
3. r – yes, that's one
4. a – no
5. w – no
6. b – no
7. e – no
8. r – yes, that's two
9. r – yes, that's three
10. y – no

Total r's = 3.

There are **3** r's in the word "strawberry".

Inference (Non-Thinking Mode)

messages = [
{"role": "user", "content": "What is the capital of France?"},
]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, enable_thinking=False)
inputs = tokenizer(text, return_tensors="pt").to(model.device)

output = model.generate(**inputs, max_new_tokens=2048, temperature=1.0, top_p=0.95, do_sample=True)
print(tokenizer.decode(output[0][inputs.input_ids.shape[-1]:], skip_special_tokens=False))

Example Output

The capital of France is Paris.

Low-Effort Thinking

messages = [
{"role": "user", "content": "What is 2 + 2?"},
]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True,
enable_thinking=True, low_effort=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)

output = model.generate(**inputs, max_new_tokens=4096, temperature=1.0, top_p=0.95, do_sample=True)
print(tokenizer.decode(output[0][inputs.input_ids.shape[-1]:], skip_special_tokens=False))

Example Output

Simple answer.

2 + 2 = 4.

---

Tool Calling with Integrated Reasoning

Granite-4.2 support tool calling with integrated reasoning — the model thinks about which tool to call and why before making the call. Tools are defined using the OpenAI function definition schema.

tools = [
{
"type": "function",
"function": {
"name": "get_current_weather",
"description": "Get the current weather for a specified city.",
"parameters": {
"type": "object",
"properties": {
"city": {"type": "string", "description": "Name of the city"}
},
"required": ["city"]
}
}
}
]

messages = [
{"role": "user", "content": "What's the weather like in Boston right now?"},
]
text = tokenizer.apply_chat_template(messages, tokenize=False, tools=tools, add_generation_prompt=True, enable_thinking=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)

output = model.generate(**inputs, max_new_tokens=4096, temperature=1.0, top_p=0.95, do_sample=True)
print(tokenizer.decode(output[0][inputs.input_ids.shape[-1]:], skip_special_tokens=False))

Example Output

Okay, the user is asking for the weather in Boston right now. Let me check the tools
available. There's a function called get_current_weather that takes a city parameter.
I need to call that with the city set to Boston.


Boston

Multi-Turn with Tool Response

messages = [
{"role": "user", "content": "What's the weather like in Boston right now?"},
{"role": "assistant", "content": "\nThe user wants to know the current weather in Boston. I should call get_current_weather.\n",
"tool_calls": [{"function": {"name": "get_current_weather", "arguments": {"city": "Boston"}}}]},
{"role": "tool", "content": '{"temperature": "72°F", "condition": "Partly cloudy", "humidity": "65%"}'},
]
text = tokenizer.apply_chat_template(messages, tokenize=False, tools=tools,
add_generation_prompt=True,...