granite-3.3-8b-base GGUF Models

Model Generation Details

This model was generated using llama.cpp at commit 5dd942de.


Quantization Beyond the IMatrix

I've been experimenting with a new quantization approach that selectively elevates the precision of key layers beyond what the default IMatrix configuration provides.

In my testing, standard IMatrix quantization underperforms at lower bit depths, especially with Mixture of Experts (MoE) models. To address this, I'm using the --tensor-type option in llama.cpp to manually "bump" important layers to higher precision. You can see the implementation here:
👉 Layer bumping with llama.cpp

While this does increase model file size, it significantly improves precision for a given quantization level.

I'd love your feedback—have you tried this? How does it perform for you?


Click here to get info on choosing the right GGUF model format

Granite-3.3-8B-Base

Model Summary:

Granite-3.3-8B-Base is a decoder-only language model with a 128K token context window. It improves upon Granite-3.1-8B-Base by adding support for Fill-in-the-Middle (FIM) using specialized tokens, enabling the model to generate content conditioned on both prefix and suffix. This makes it well-suited for code completion tasks.

Supported Languages: English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, and Chinese. Users may finetune Granite 3.3 models for languages beyond these 12 languages.

Intended Use: Prominent use cases of LLMs in text-to-text generation include summarization, text classification, extraction, question-answering, and other long-context tasks. All Granite Base models are able to handle these tasks as they were trained on a large amount of data from various domains. Moreover, they can serve as baseline to create specialized models for specific application scenarios.

Generation: This is a simple example of how to use Granite-3.3-8B-Base model.

Install the following libraries:

pip install torch torchvision torchaudio
pip install accelerate
pip install transformers

Then, copy the code snippet below to run the example.

from transformers import AutoModelForCausalLM, AutoTokenizer
device = "auto"
model_path = "ibm-granite/granite-3.3-8b-base"
tokenizer = AutoTokenizer.from_pretrained(model_path)
# drop device_map if running on CPU
model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device)
model.eval()
# change input text as desired
input_text = "Where is the Thomas J. Watson Research Center located?"
# tokenize the text
input_tokens = tokenizer(input_text, return_tensors="pt").to(device)
# generate output tokens
output = model.generate(**input_tokens,
                        max_length=4000)
# decode output tokens into text
output = tokenizer.batch_decode(output)
# print output
print(output)

Evaluation Results:

Comparison with 3.1 Base models1
Models ARC-Challenge Hellaswag MMLU TruthfulQA Winogrande GSM8K DROP NQ AGIEval TriviaQA Avg
Granite-3.1-2B-Base 46.83 74.9 54.87 38.93 71.8 53.0 30.08 24.46 38.24 63.18 49.63
Granite-3.3-2B-Base 47.49 73.2 54.33 40.83 70.4 50.0 32.552 24.36 38.78 63.22 49.52
Granite-3.1-8B-Base 53.51 81.4 64.28 51.27 76.2 70.5 45.87 35.97 48.99 78.33 60.63
Granite-3.3-8B-Base 50.84 80.1 63.89 52.15 74.4 59.0 36.14 36.5 49.3 78.18 58.05

Model Architecture: Granite-3.3-8B-Base is based on a decoder-only dense transformer architecture. Core components of this architecture are: GQA and RoPE, MLP with SwiGLU, RMSNorm, and shared input/output embeddings.

Model 2B Dense 8B Dense
Embedding size 2048 4096
Number of layers 40 40
Attention head size 64 128
Number of attention heads 32 32
Number of KV heads 8 8
MLP hidden size 8192 12800
MLP activation SwiGLU SwiGLU
Initialization std 0.1 0.1
Sequence length 128K 128K
Position embedding RoPE RoPE
# Parameters 2.5B 8.1B
# Active parameters 2.5B 8.1B
# Training tokens 12T 12T

Training Data: This model is trained on a mix of open source and proprietary data following a three-stage training strategy.

  • Stage 1 data: The data for stage 1 is sourced from diverse domains, such as: web, code, academic sources, books, and math data.
  • Stage 2 data: The data for stage 2 comprises a curated mix of high-quality data from the same domains, plus multilingual and instruction data. The goal of this second training phase is to enhance the model’s performance on specific tasks.
  • Stage 3 data: The data for stage 3 consists of original stage-2 pretraining data with additional synthetic long-context data in form of QA/summary pairs where the answer contains a recitation of the related paragraph before the answer.

Infrastructure: We train Granite 3.3 Language Models 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: The use of Large Language Models involves risks and ethical considerations people must be aware of, including but not limited to: bias and fairness, misinformation, and autonomous decision-making. Granite-3.3-8B-Base model is not the exception in this regard. Even though this model is suited for multiple generative AI tasks, it has not undergone any safety alignment, there it may produce problematic outputs. Additionally, it remains uncertain whether smaller models might exhibit increased susceptibility to hallucination in generation scenarios by copying text verbatim from the training dataset due to their reduced sizes and memorization capacities. This aspect is currently an active area of research, and we anticipate more rigorous exploration, comprehension, and mitigations in this domain. Regarding ethics, a latent risk associated with all Large Language Models is their malicious utilization. We urge the community to use Granite-3.3-8B-Base model with ethical intentions and in a responsible way.

Resources

[1] Evaluated using OLMES


🚀 If you find these models useful

Help me test my AI-Powered Quantum Network Monitor Assistant with quantum-ready security checks:

👉 Quantum Network Monitor

The full Open Source Code for the Quantum Network Monitor Service available at my github repos ( repos with NetworkMonitor in the name) : Source Code Quantum Network Monitor. You will also find the code I use to quantize the models if you want to do it yourself GGUFModelBuilder

💬 How to test:
Choose an AI assistant type:

  • TurboLLM (GPT-4.1-mini)
  • HugLLM (Hugginface Open-source models)
  • TestLLM (Experimental CPU-only)

What I’m Testing

I’m pushing the limits of small open-source models for AI network monitoring, specifically:

  • Function calling against live network services
  • How small can a model go while still handling:
    • Automated Nmap security scans
    • Quantum-readiness checks
    • Network Monitoring tasks

🟡 TestLLM – Current experimental model (llama.cpp on 2 CPU threads on huggingface docker space):

  • Zero-configuration setup
  • ⏳ 30s load time (slow inference but no API costs) . No token limited as the cost is low.
  • 🔧 Help wanted! If you’re into edge-device AI, let’s collaborate!

Other Assistants

🟢 TurboLLM – Uses gpt-4.1-mini :

  • **It performs very well but unfortunatly OpenAI charges per token. For this reason tokens usage is limited.
  • Create custom cmd processors to run .net code on Quantum Network Monitor Agents
  • Real-time network diagnostics and monitoring
  • Security Audits
  • Penetration testing (Nmap/Metasploit)

🔵 HugLLM – Latest Open-source models:

  • 🌐 Runs on Hugging Face Inference API. Performs pretty well using the lastest models hosted on Novita.

💡 Example commands you could test:

  1. "Give me info on my websites SSL certificate"
  2. "Check if my server is using quantum safe encyption for communication"
  3. "Run a comprehensive security audit on my server"
  4. '"Create a cmd processor to .. (what ever you want)" Note you need to install a Quantum Network Monitor Agent to run the .net code on. This is a very flexible and powerful feature. Use with caution!

Final Word

I fund the servers used to create these model files, run the Quantum Network Monitor service, and pay for inference from Novita and OpenAI—all out of my own pocket. All the code behind the model creation and the Quantum Network Monitor project is open source. Feel free to use whatever you find helpful.

If you appreciate the work, please consider buying me a coffee ☕. Your support helps cover service costs and allows me to raise token limits for everyone.

I'm also open to job opportunities or sponsorship.

Thank you! 😊

Downloads last month
854
GGUF
Model size
8.17B params
Architecture
granite
Hardware compatibility
Log In to view the estimation

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including Mungert/granite-3.3-8b-base-GGUF