---
pipeline_tag: text-generation
inference: false
license: apache-2.0
tags:
- code
- language
- granite-3.2
base_model:
- ibm-granite/granite-3.2-8b-instruct
model_creator: ibm-granite
model_name: granite-3.2-8b-instruct
model_type: granite
datasets:
- m-a-p/CodeFeedback-Filtered-Instruction
quantized_by: CISC
---

# granite-3.2-8b-instruct - SOTA GGUF
- Model creator: [IBM](https://huggingface.co/ibm-granite)
- Original model: [granite-3.2-8b-instruct](https://huggingface.co/ibm-granite/granite-3.2-8b-instruct)

<!-- description start -->
## Description

This repo contains State Of The Art quantized GGUF format model files for [granite-3.2-8b-instruct](https://huggingface.co/ibm-granite/granite-3.2-8b-instruct).

Quantization was done with an importance matrix that was trained for ~1M tokens (256 batches of 4096 tokens) of answers from the [CodeFeedback-Filtered-Instruction](https://huggingface.co/datasets/m-a-p/CodeFeedback-Filtered-Instruction) dataset.

Fill-in-Middle tokens are automatically detected and supported as of commit [11ac980](https://github.com/ggerganov/llama.cpp/commit/11ac9800aff532715a5bc7991062c68ba3472e6e), see [example](#simple-llama-cpp-python-example-fill-in-middle-code).

<!-- description end -->

<!-- compatibility_gguf start -->
## Compatibility

These quantised GGUFv3 files are compatible with llama.cpp from September 17th 2024 onwards, as of commit [0d2ec43](https://github.com/ggerganov/llama.cpp/commit/0d2ec438330271d201c2e9224aca23d0d5c908bf)

They are also compatible with many third party UIs and libraries provided they are built using a recent llama.cpp.

Usage with llama-cpp-python based frameworks require [PR#1486](https://github.com/abetlen/llama-cpp-python/pull/1486) patched in for the chat template to work correctly.

## Explanation of quantisation methods

<details>
  <summary>Click to see details</summary>

The new methods available are:

* GGML_TYPE_IQ1_S - 1-bit quantization in super-blocks with an importance matrix applied, effectively using 1.56 bits per weight (bpw)
* GGML_TYPE_IQ1_M - 1-bit quantization in super-blocks with an importance matrix applied, effectively using 1.75 bpw
* GGML_TYPE_IQ2_XXS - 2-bit quantization in super-blocks with an importance matrix applied, effectively using 2.06 bpw
* GGML_TYPE_IQ2_XS - 2-bit quantization in super-blocks with an importance matrix applied, effectively using 2.31 bpw
* GGML_TYPE_IQ2_S - 2-bit quantization in super-blocks with an importance matrix applied, effectively using 2.5 bpw
* GGML_TYPE_IQ2_M - 2-bit quantization in super-blocks with an importance matrix applied, effectively using 2.7 bpw
* GGML_TYPE_IQ3_XXS - 3-bit quantization in super-blocks with an importance matrix applied, effectively using 3.06 bpw
* GGML_TYPE_IQ3_XS - 3-bit quantization in super-blocks with an importance matrix applied, effectively using 3.3 bpw
* GGML_TYPE_IQ3_S - 3-bit quantization in super-blocks with an importance matrix applied, effectively using 3.44 bpw
* GGML_TYPE_IQ3_M - 3-bit quantization in super-blocks with an importance matrix applied, effectively using 3.66 bpw
* GGML_TYPE_IQ4_XS - 4-bit quantization in super-blocks with an importance matrix applied, effectively using 4.25 bpw
* GGML_TYPE_IQ4_NL - 4-bit non-linearly mapped quantization with an importance matrix applied, effectively using 4.5 bpw

Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->

<!-- README_GGUF.md-provided-files start -->
## Provided files

| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [granite-3.2-8b-instruct.IQ1_S.gguf](https://huggingface.co/CISCai/granite-3.2-8b-instruct-SOTA-GGUF/blob/main/granite-3.2-8b-instruct.IQ1_S.gguf) | IQ1_S | 1 | 1.7 GB| 1.9 GB | smallest, significant quality loss |
| [granite-3.2-8b-instruct.IQ1_M.gguf](https://huggingface.co/CISCai/granite-3.2-8b-instruct-SOTA-GGUF/blob/main/granite-3.2-8b-instruct.IQ1_M.gguf) | IQ1_M | 1 | 1.8 GB| 2.1 GB | very small, significant quality loss |
| [granite-3.2-8b-instruct.IQ2_XXS.gguf](https://huggingface.co/CISCai/granite-3.2-8b-instruct-SOTA-GGUF/blob/main/granite-3.2-8b-instruct.IQ2_XXS.gguf) | IQ2_XXS | 2 | 2.1 GB| 2.3 GB | very small, high quality loss |
| [granite-3.2-8b-instruct.IQ2_XS.gguf](https://huggingface.co/CISCai/granite-3.2-8b-instruct-SOTA-GGUF/blob/main/granite-3.2-8b-instruct.IQ2_XS.gguf) | IQ2_XS | 2 | 2.3 GB| 2.5 GB | very small, high quality loss |
| [granite-3.2-8b-instruct.IQ2_S.gguf](https://huggingface.co/CISCai/granite-3.2-8b-instruct-SOTA-GGUF/blob/main/granite-3.2-8b-instruct.IQ2_S.gguf) | IQ2_S | 2 | 2.4 GB| 2.7 GB | small, substantial quality loss |
| [granite-3.2-8b-instruct.IQ2_M.gguf](https://huggingface.co/CISCai/granite-3.2-8b-instruct-SOTA-GGUF/blob/main/granite-3.2-8b-instruct.IQ2_M.gguf) | IQ2_M | 2 | 2.6 GB| 2.9 GB | small, greater quality loss |
| [granite-3.2-8b-instruct.IQ3_XXS.gguf](https://huggingface.co/CISCai/granite-3.2-8b-instruct-SOTA-GGUF/blob/main/granite-3.2-8b-instruct.IQ3_XXS.gguf) | IQ3_XXS | 3 | 3.0 GB| 3.2 GB | very small, high quality loss |
| [granite-3.2-8b-instruct.IQ3_XS.gguf](https://huggingface.co/CISCai/granite-3.2-8b-instruct-SOTA-GGUF/blob/main/granite-3.2-8b-instruct.IQ3_XS.gguf) | IQ3_XS | 3 | 3.2 GB| 3.4 GB | small, substantial quality loss |
| [granite-3.2-8b-instruct.IQ3_S.gguf](https://huggingface.co/CISCai/granite-3.2-8b-instruct-SOTA-GGUF/blob/main/granite-3.2-8b-instruct.IQ3_S.gguf) | IQ3_S | 3 | 3.4 GB| 3.6 GB | small, greater quality loss |
| [granite-3.2-8b-instruct.IQ3_M.gguf](https://huggingface.co/CISCai/granite-3.2-8b-instruct-SOTA-GGUF/blob/main/granite-3.2-8b-instruct.IQ3_M.gguf) | IQ3_M | 3 | 3.5 GB| 3.7 GB | medium, balanced quality - recommended |
| [granite-3.2-8b-instruct.IQ4_XS.gguf](https://huggingface.co/CISCai/granite-3.2-8b-instruct-SOTA-GGUF/blob/main/granite-3.2-8b-instruct.IQ4_XS.gguf) | IQ4_XS | 4 | 4.1 GB| 4.3 GB | small, substantial quality loss |

Generated importance matrix file: [granite-3.2-8b-instruct.imatrix.dat](https://huggingface.co/CISCai/granite-3.2-8b-instruct-SOTA-GGUF/blob/main/granite-3.2-8b-instruct.imatrix.dat)

**Note**: the above RAM figures assume no GPU offloading with 4K context. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.

<!-- README_GGUF.md-provided-files end -->

<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command

Make sure you are using `llama.cpp` from commit [6171c9d](https://github.com/ggerganov/llama.cpp/commit/6171c9d25820ccf676b243c172868819d882848f) or later for jinja2 chat template support.

```shell
./llama-cli -ngl 41 -m granite-3.2-8b-instruct.IQ4_XS.gguf --color -c 131072 -cnv --jinja"
```

Change `-ngl 41` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.

Change `-c 131072` to the desired sequence length.

If you are low on V/RAM try quantizing the K-cache with `-ctk q8_0` or even `-ctk q4_0` for big memory savings (depending on context size).
There is a similar option for V-cache (`-ctv`), only available if you enable Flash Attention (`-fa`) as well.

For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)

## How to run from Python code

You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) module.

### How to load this model in Python code, using llama-cpp-python

For full documentation, please see: [llama-cpp-python docs](https://llama-cpp-python.readthedocs.io/en/latest/).

#### First install the package

Run one of the following commands, according to your system:

```shell
# Prebuilt wheel with basic CPU support
pip install llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
# Prebuilt wheel with NVidia CUDA acceleration
pip install llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cu121 (or cu122 etc.)
# Prebuilt wheel with Metal GPU acceleration
pip install llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/metal
# Build base version with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DGGML_CUDA=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DGGML_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DGGML_METAL=on" pip install llama-cpp-python
# Or with Vulkan acceleration
CMAKE_ARGS="-DGGML_VULKAN=on" pip install llama-cpp-python
# Or with SYCL acceleration
CMAKE_ARGS="-DGGML_SYCL=on -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx" pip install llama-cpp-python

# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DGGML_CUDA=on"
pip install llama-cpp-python
```

#### Simple llama-cpp-python example code

```python
from llama_cpp import Llama

# Chat Completion API

llm = Llama(model_path="./granite-3.2-8b-instruct.IQ4_XS.gguf", n_gpu_layers=41, n_ctx=131072)
print(llm.create_chat_completion(
    repeat_penalty = 1.0,
    messages = [
        {
            "role": "user",
            "content": "Pick a LeetCode challenge and solve it in Python."
        }
    ]
))
```

#### Simple llama-cpp-python example fill-in-middle code

```python
from llama_cpp import Llama

# Completion API

prompt = "def add("
suffix = "\n    return sum\n\n"

llm = Llama(model_path="./granite-3.2-8b-instruct.IQ4_XS.gguf", n_gpu_layers=41, n_ctx=131072)
output = llm.create_completion(
    temperature = 0.0,
    repeat_penalty = 1.0,
    prompt = prompt,
    suffix = suffix
)

# Models sometimes repeat suffix in response, attempt to filter that
response = output["choices"][0]["text"]
response_stripped = response.rstrip()
unwanted_response_suffix = suffix.rstrip()
unwanted_response_length = len(unwanted_response_suffix)

filtered = False
if unwanted_response_suffix and response_stripped[-unwanted_response_length:] == unwanted_response_suffix:
    response = response_stripped[:-unwanted_response_length]
    filtered = True

print(f"Fill-in-Middle completion{' (filtered)' if filtered else ''}:\n\n{prompt}\033[32m{response}\033[{'33' if filtered else '0'}m{suffix}\033[0m")
```

#### Simple llama-cpp-python example function calling code

```python
from llama_cpp import Llama

# Chat Completion API

grammar = LlamaGrammar.from_json_schema(json.dumps({
    "type": "array",
    "items": {
        "type": "object",
        "required": [ "name", "arguments" ],
        "properties": {
            "name": {
                "type": "string"
            },
            "arguments": {
                "type": "object"
            }
        }
    }
}))

llm = Llama(model_path="./granite-3.2-8b-instruct.IQ4_XS.gguf", n_gpu_layers=41, n_ctx=131072)
response = llm.create_chat_completion(
      temperature = 0.0,
      repeat_penalty = 1.0,
      messages = [
        {
          "role": "user",
          "content": "What's the weather like in Oslo and Stockholm?"
        }
      ],
      tools=[{
        "type": "function",
        "function": {
          "name": "get_current_weather",
          "description": "Get the current weather in a given location",
          "parameters": {
            "type": "object",
            "properties": {
              "location": {
                "type": "string",
                "description": "The city and state, e.g. San Francisco, CA"
              },
              "unit": {
                "type": "string",
                "enum": [ "celsius", "fahrenheit" ]
              }
            },
            "required": [ "location" ]
          }
        }
      }],
      grammar = grammar
)
print(json.loads(response["choices"][0]["text"]))

print(llm.create_chat_completion(
      temperature = 0.0,
      repeat_penalty = 1.0,
      messages = [
        {
          "role": "user",
          "content": "What's the weather like in Oslo?"
        },
        { # The tool_calls is from the response to the above with tool_choice active
          "role": "assistant",
          "content": None,
          "tool_calls": [
            {
              "id": "call__0_get_current_weather_cmpl-...",
              "type": "function",
              "function": {
                "name": "get_current_weather",
                "arguments": { "location": "Oslo, Norway" , "unit": "celsius" }
              }
            }
          ]
        },
        { # The tool_call_id is from tool_calls and content is the result from the function call you made
          "role": "tool",
          "content": "20",
          "tool_call_id": "call__0_get_current_weather_cmpl-..."
        }
      ],
      tools=[{
        "type": "function",
        "function": {
          "name": "get_current_weather",
          "description": "Get the current weather in a given location",
          "parameters": {
            "type": "object",
            "properties": {
              "location": {
                "type": "string",
                "description": "The city and state, e.g. San Francisco, CA"
              },
              "unit": {
                "type": "string",
                "enum": [ "celsius", "fahrenheit" ]
              }
            },
            "required": [ "location" ]
          }
        }
      }],
      #tool_choice={
      #  "type": "function",
      #  "function": {
      #    "name": "get_current_weather"
      #  }
      #}
))
```

#### Simple llama-cpp-python RAG code, requires [PR#1440](https://github.com/abetlen/llama-cpp-python/pull/1440)

```python
from llama_cpp import Llama

llm = Llama(model_path="./granite-3.2-8b-instruct.IQ4_XS.gguf", n_gpu_layers=41, n_ctx=131072)

print(llm.create_chat_completion(
    messages = [
        {
            "role": "user",
            "content": "Write a short summary of each document please."
        }
    ],
    documents = [
        {
            "text": "Lorem ipsum",
        },
        {
            "text": "Dolor sit amet",
        }
    ]
))
```

#### Simple llama-cpp-python reasoning code, requires [PR#1440](https://github.com/abetlen/llama-cpp-python/pull/1440)

```python
from llama_cpp import Llama

llm = Llama(model_path="./granite-3.2-8b-instruct.IQ4_XS.gguf", n_gpu_layers=41, n_ctx=131072)

print(llm.create_chat_completion(
    messages = [
        {
            "role": "user",
            "content": "You have 10 liters of a 30% acid solution. How many liters of a 70% acid solution must be added to achieve a 50% acid mixture?"
        }
    ],
    template_kwargs = {
        "thinking": True
    }
))
```

<!-- README_GGUF.md-how-to-run end -->

<!-- original-model-card start -->
# Granite-3.2-8B-Instruct

**Model Summary:**
Granite-3.2-8B-Instruct is an 8-billion-parameter, long-context AI model fine-tuned for thinking capabilities. Built on top of [Granite-3.1-8B-Instruct](https://huggingface.co/ibm-granite/granite-3.1-8b-instruct), it has been trained using a mix of permissively licensed open-source datasets and internally generated synthetic data designed for reasoning tasks. The model allows controllability of its thinking capability, ensuring it is applied only when required.


- **Developers:** Granite Team, IBM
- **Website**: [Granite Docs](https://www.ibm.com/granite/docs/)
- **Release Date**: February 26th, 2025
- **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)

**Supported Languages:** 
English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, and Chinese. However, users may finetune this Granite model for languages beyond these 12 languages.

**Intended Use:** 
This model is designed to handle general instruction-following tasks and can be integrated into AI assistants across various domains, including business applications.

**Capabilities**
* **Thinking**
* Summarization
* Text classification
* Text extraction
* Question-answering
* Retrieval Augmented Generation (RAG)
* Code related tasks
* Function-calling tasks
* Multilingual dialog use cases
* Long-context tasks including long document/meeting summarization, long document QA, etc.



**Generation:** 
This is a simple example of how to use Granite-3.2-8B-Instruct model.

Install the following libraries:

```shell
pip install torch torchvision torchaudio
pip install accelerate
pip install transformers
```
Then, copy the snippet from the section that is relevant for your use case.

```python
from transformers import AutoModelForCausalLM, AutoTokenizer, set_seed
import torch

model_path="ibm-granite/granite-3.2-8b-instruct"
device="cuda"
model = AutoModelForCausalLM.from_pretrained(
        model_path,
        device_map=device,
        torch_dtype=torch.bfloat16,
    )
tokenizer = AutoTokenizer.from_pretrained(
        model_path
)

conv = [{"role": "user", "content":"You have 10 liters of a 30% acid solution. How many liters of a 70% acid solution must be added to achieve a 50% acid mixture?"}]

input_ids = tokenizer.apply_chat_template(conv, return_tensors="pt", thinking=True, return_dict=True, add_generation_prompt=True).to(device)

set_seed(42)
output = model.generate(
    **input_ids,
    max_new_tokens=8192,
)

prediction = tokenizer.decode(output[0, input_ids["input_ids"].shape[1]:], skip_special_tokens=True)
print(prediction)
```

**Example Outputs**
- thinking=True
```md
Here is my thought process:

1. We know we start with 10 liters of a 30% acid solution, so there's 3 liters of pure acid in it (10 liters * 0.3).
2. We need to determine how much of the 70% acid solution to add such that the final mixture is 50% acid.
3. Let's say x liters of the 70% acid solution are added. This will contribute 0.7x liters of pure acid.
4. The total volume of the new mixture will be 10 + x liters, and the total amount of pure acid will be 3 + 0.7x liters.
5. We need to set up an equation where (3 + 0.7x) / (10 + x) = 0.5 (since we want a 50% acid mixture).
6. Solving this equation for x will give us the volume of 70% solution needed.

Here is my response:

To solve this, we need to set up an equation based on the concentration of acid before and after mixing. 

1. **Initial Acid Content**: 
   - We start with 10 liters of a 30% acid solution. 
   - Pure acid in this = 10 * 0.3 = 3 liters.

2. **Variable for Addition**:
   - Let x be the liters of 70% acid solution to be added.
   - Pure acid in x liters of 70% solution = 0.7x liters.

3. **Final Mixture Concentration**:
   - Total volume of mixture = 10 + x liters.
   - Total pure acid in the mixture = 3 (from initial solution) + 0.7x (from added solution).

4. **Setting up the equation for 50% acid concentration**:
   - We require that the ratio of pure acid to total volume is 0.5 (50%).
   - Therefore, the equation is:

   \[
   \frac{3 + 0.7x}{10 + x} = 0.5
   \]

5. **Solving the equation**:

   Multiply both sides by (10 + x) to clear the fraction:

   \[
   3 + 0.7x = 0.5(10 + x)
   \]

   Expanding the right side:

   \[
   3 + 0.7x = 5 + 0.5x
   \]

   Subtract 0.5x from both sides:

   \[
   3 + 0.2x = 5
   \]

   Subtract 3 from both sides:

   \[
   0.2x = 2
   \]

   Divide by 0.2:

   \[
   x = 10
   \]

So, 10 liters of the 70% acid solution must be added to the initial 10 liters of 30% solution to get a 50% acid mixture. 

Let's verify: 

- Initial acid: 3 liters
- Acid from added solution: 0.7 * 10 = 7 liters
- Total acid: 3 + 7 = 10 liters
- Total volume: 10 + 10 = 20 liters
- Acid percentage: \(\frac{10}{20} = 0.5 = 50\%\)

This confirms our solution. 

Final answer: 10 liters of 70% acid solution should be added.
```
- thinking=False
```md
Let's denote the amount of 70% acid solution to be added as x liters.

We start with 10 liters of a 30% acid solution, which means there are 0.3 * 10 = 3 liters of pure acid in it.

We want to end up with a 50% acid solution after adding x liters of 70% acid solution. The total volume of the mixture will be 10 + x liters, and we want half of this volume to be pure acid.

So, the amount of pure acid in the final mixture should be 0.5 * (10 + x) liters.

The amount of pure acid in the final mixture comes from two sources: the original 30% solution and the added 70% solution. So, we can set up the following equation:

3 (from the original solution) + 0.7x (from the added solution) = 0.5 * (10 + x)

Now, let's solve for x:

3 + 0.7x = 5 + 0.5x
0.7x - 0.5x = 5 - 3
0.2x = 2
x = 2 / 0.2
x = 10

So, you need to add 10 liters of a 70% acid solution to the 10 liters of a 30% acid solution to get a 50% acid mixture.
```

**Evaluation Results:**
<table>
  
<thead>
  <tr>
    <th style="text-align:left; background-color: #001d6c; color: white;">Models</th>
    <th style="text-align:center; background-color: #001d6c; color: white;">ArenaHard</th>
    <th style="text-align:center; background-color: #001d6c; color: white;">Alpaca-Eval-2</th>
    <th style="text-align:center; background-color: #001d6c; color: white;">MMLU</th>
    <th style="text-align:center; background-color: #001d6c; color: white;">PopQA</th>
    <th style="text-align:center; background-color: #001d6c; color: white;">TruthfulQA</th>
    <th style="text-align:center; background-color: #001d6c; color: white;">BigBenchHard</th>
    <th style="text-align:center; background-color: #001d6c; color: white;">DROP</th>
    <th style="text-align:center; background-color: #001d6c; color: white;">GSM8K</th>
    <th style="text-align:center; background-color: #001d6c; color: white;">HumanEval</th>
   <th style="text-align:center; background-color: #001d6c; color: white;">HumanEval+</th>
  <th style="text-align:center; background-color: #001d6c; color: white;">IFEval</th>
    <th style="text-align:center; background-color: #001d6c; color: white;">AttaQ</th>
  </tr></thead>
  <tbody>
  <tr>
    <td style="text-align:left; background-color: #DAE8FF; color: black;">Llama-3.1-8B-Instruct</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">36.43</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">27.22</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">69.15</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">28.79</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">52.79</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">72.66</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">61.48</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">83.24</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">85.32</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">80.15</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">79.10</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">83.43</td>
  </tr>
           
  <tr>
    <td style="text-align:left; background-color: #DAE8FF; color: black;">DeepSeek-R1-Distill-Llama-8B</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">17.17</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">21.85</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">45.80</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">13.25</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">47.43</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">65.71</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">44.46</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">72.18</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">67.54</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">62.91</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">66.50</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">42.87</td>
  </tr>
      
  <tr>
    <td style="text-align:left; background-color: #DAE8FF; color: black;">Qwen-2.5-7B-Instruct</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">25.44</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">30.34</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">74.30</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">18.12</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">63.06</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">70.40</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">54.71</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">84.46</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">93.35</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">89.91</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">74.90</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">81.90</td>
  </tr>
      
  <tr>
    <td style="text-align:left; background-color: #DAE8FF; color: black;">DeepSeek-R1-Distill-Qwen-7B</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">10.36</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">15.35</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">50.72</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">9.94</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">47.14</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">65.04</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">42.76</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">78.47</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">79.89</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">78.43</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">59.10</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">42.45</td>
  </tr>

  <tr>
    <td style="text-align:left; background-color: #DAE8FF; color: black;">Granite-3.1-8B-Instruct</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">37.58</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">30.34</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">66.77</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">28.7</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">65.84</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">68.55</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">50.78</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">79.15</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">89.63</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">85.79</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">73.20</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">85.73</td>
  </tr>
      
      
<tr>
    <td style="text-align:left; background-color: #DAE8FF; color: black;">Granite-3.1-2B-Instruct</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">23.3</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">27.17</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">57.11</td> 
    <td style="text-align:center; background-color: #DAE8FF; color: black;">20.55</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">59.79</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">54.46</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">18.68</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">67.55</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">79.45</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">75.26</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">63.59</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">84.7</td>
  </tr>
      
 
  <tr>
      <td style="text-align:left; background-color: #DAE8FF; color: black;">Granite-3.2-2B-Instruct</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">24.86</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">34.51</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">57.18</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">20.56</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">59.8</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">52.27</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">21.12</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">67.02</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">80.13</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">73.39</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">61.55</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">83.23</td>
  </tr> 
      
<tr>
      <td style="text-align:left; background-color: #DAE8FF; color: black;"><b>Granite-3.2-8B-Instruct</b></td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">55.25</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">61.19</td>
   <td style="text-align:center; background-color: #DAE8FF; color: black;">66.79</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">28.04</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">66.92</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">64.77</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">50.95</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">81.65</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">89.35</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">85.72</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">74.31</td>
    <td style="text-align:center; background-color: #DAE8FF; color: black;">85.42</td>
 
  </tr>

     
      
</tbody></table>

**Training Data:** 
Overall, our training data is largely comprised of two key sources: (1) publicly available datasets with permissive license, (2) internal synthetically generated data targeted to enhance reasoning capabilites. 
<!-- A detailed attribution of datasets can be found in [Granite 3.2 Technical Report (coming soon)](#), and [Accompanying Author List](https://github.com/ibm-granite/granite-3.0-language-models/blob/main/author-ack.pdf). -->

**Infrastructure:**
We train Granite-3.2-8B-Instruct using IBM's super computing cluster, Blue Vela, which is outfitted with NVIDIA H100 GPUs. This cluster provides a scalable and efficient infrastructure for training our models over thousands of GPUs.

**Ethical Considerations and Limitations:** 
Granite-3.2-8B-Instruct builds upon Granite-3.1-8B-Instruct, leveraging both permissively licensed open-source and select proprietary data for enhanced performance. Since it inherits its foundation from the previous model, all ethical considerations and limitations applicable to [Granite-3.1-8B-Instruct](https://huggingface.co/ibm-granite/granite-3.1-8b-instruct) remain relevant.


**Resources**
- ⭐️ Learn about the latest updates with Granite: https://www.ibm.com/granite
- 📄 Get started with tutorials, best practices, and prompt engineering advice: https://www.ibm.com/granite/docs/
- 💡 Learn about the latest Granite learning resources: https://ibm.biz/granite-learning-resources

<!-- ## Citation
```
@misc{granite-models,
  author = {author 1, author2, ...},
  title = {},
  journal = {},
  volume = {},
  year = {2024},
  url = {https://arxiv.org/abs/0000.00000},
}
``` -->