granite-3.2-2b-instruct GGUF Models

Choosing the Right Model Format

Selecting the correct model format depends on your hardware capabilities and memory constraints.

BF16 (Brain Float 16) – Use if BF16 acceleration is available

A 16-bit floating-point format designed for faster computation while retaining good precision.
Provides similar dynamic range as FP32 but with lower memory usage.
Recommended if your hardware supports BF16 acceleration (check your device's specs).
Ideal for high-performance inference with reduced memory footprint compared to FP32.

📌 Use BF16 if:
✔ Your hardware has native BF16 support (e.g., newer GPUs, TPUs).
✔ You want higher precision while saving memory.
✔ You plan to requantize the model into another format.

📌 Avoid BF16 if:
❌ Your hardware does not support BF16 (it may fall back to FP32 and run slower).
❌ You need compatibility with older devices that lack BF16 optimization.

F16 (Float 16) – More widely supported than BF16

A 16-bit floating-point high precision but with less of range of values than BF16.
Works on most devices with FP16 acceleration support (including many GPUs and some CPUs).
Slightly lower numerical precision than BF16 but generally sufficient for inference.

📌 Use F16 if:
✔ Your hardware supports FP16 but not BF16.
✔ You need a balance between speed, memory usage, and accuracy.
✔ You are running on a GPU or another device optimized for FP16 computations.

📌 Avoid F16 if:
❌ Your device lacks native FP16 support (it may run slower than expected).
❌ You have memory limitations.

Quantized Models (Q4_K, Q6_K, Q8, etc.) – For CPU & Low-VRAM Inference

Quantization reduces model size and memory usage while maintaining as much accuracy as possible.

Lower-bit models (Q4_K) → Best for minimal memory usage, may have lower precision.
Higher-bit models (Q6_K, Q8_0) → Better accuracy, requires more memory.

📌 Use Quantized Models if:
✔ You are running inference on a CPU and need an optimized model.
✔ Your device has low VRAM and cannot load full-precision models.
✔ You want to reduce memory footprint while keeping reasonable accuracy.

📌 Avoid Quantized Models if:
❌ You need maximum accuracy (full-precision models are better for this).
❌ Your hardware has enough VRAM for higher-precision formats (BF16/F16).

Very Low-Bit Quantization (IQ3_XS, IQ3_S, IQ3_M, Q4_K, Q4_0)

These models are optimized for extreme memory efficiency, making them ideal for low-power devices or large-scale deployments where memory is a critical constraint.

IQ3_XS: Ultra-low-bit quantization (3-bit) with extreme memory efficiency.
- Use case: Best for ultra-low-memory devices where even Q4_K is too large.
- Trade-off: Lower accuracy compared to higher-bit quantizations.
IQ3_S: Small block size for maximum memory efficiency.
- Use case: Best for low-memory devices where IQ3_XS is too aggressive.
IQ3_M: Medium block size for better accuracy than IQ3_S.
- Use case: Suitable for low-memory devices where IQ3_S is too limiting.
Q4_K: 4-bit quantization with block-wise optimization for better accuracy.
- Use case: Best for low-memory devices where Q6_K is too large.
Q4_0: Pure 4-bit quantization, optimized for ARM devices.
- Use case: Best for ARM-based devices or low-memory environments.

Summary Table: Model Format Selection

Model Format	Precision	Memory Usage	Device Requirements	Best Use Case
BF16	Highest	High	BF16-supported GPU/CPUs	High-speed inference with reduced memory
F16	High	High	FP16-supported devices	GPU inference when BF16 isn't available
Q4_K	Medium Low	Low	CPU or Low-VRAM devices	Best for memory-constrained environments
Q6_K	Medium	Moderate	CPU with more memory	Better accuracy while still being quantized
Q8_0	High	Moderate	CPU or GPU with enough VRAM	Best accuracy among quantized models
IQ3_XS	Very Low	Very Low	Ultra-low-memory devices	Extreme memory efficiency and low accuracy
Q4_0	Low	Low	ARM or low-memory devices	llama.cpp can optimize for ARM devices

Included Files & Details

`granite-3.2-2b-instruct-bf16.gguf`

Model weights preserved in BF16.
Use this if you want to requantize the model into a different format.
Best if your device supports BF16 acceleration.

`granite-3.2-2b-instruct-f16.gguf`

Model weights stored in F16.
Use if your device supports FP16, especially if BF16 is not available.

`granite-3.2-2b-instruct-bf16-q8_0.gguf`

Output & embeddings remain in BF16.
All other layers quantized to Q8_0.
Use if your device supports BF16 and you want a quantized version.

`granite-3.2-2b-instruct-f16-q8_0.gguf`

Output & embeddings remain in F16.
All other layers quantized to Q8_0.

`granite-3.2-2b-instruct-q4_k.gguf`

Output & embeddings quantized to Q8_0.
All other layers quantized to Q4_K.
Good for CPU inference with limited memory.

`granite-3.2-2b-instruct-q4_k_s.gguf`

Smallest Q4_K variant, using less memory at the cost of accuracy.
Best for very low-memory setups.

`granite-3.2-2b-instruct-q6_k.gguf`

Output & embeddings quantized to Q8_0.
All other layers quantized to Q6_K .

`granite-3.2-2b-instruct-q8_0.gguf`

Fully Q8 quantized model for better accuracy.
Requires more memory but offers higher precision.

`granite-3.2-2b-instruct-iq3_xs.gguf`

IQ3_XS quantization, optimized for extreme memory efficiency.
Best for ultra-low-memory devices.

`granite-3.2-2b-instruct-iq3_m.gguf`

IQ3_M quantization, offering a medium block size for better accuracy.
Suitable for low-memory devices.

`granite-3.2-2b-instruct-q4_0.gguf`

Pure Q4_0 quantization, optimized for ARM devices.
Best for low-memory environments.
Prefer IQ4_NL for better accuracy.

🚀 If you find these models useful

❤ Please click "Like" if you find this useful!
Help me test my AI-Powered Network Monitor Assistant with quantum-ready security checks:
👉 Free Network Monitor

💬 How to test:

Click the chat icon (bottom right on any page)
Choose an AI assistant type:
- TurboLLM (GPT-4-mini)
- FreeLLM (Open-source)
- 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 scans
- Quantum-readiness checks
- Metasploit integration

🟡 TestLLM – Current experimental model (llama.cpp on 6 CPU threads):

✅ Zero-configuration setup
⏳ 30s load time (slow inference but no API costs)
🔧 Help wanted! If you’re into edge-device AI, let’s collaborate!

Other Assistants

🟢 TurboLLM – Uses gpt-4-mini for:

Real-time network diagnostics
Automated penetration testing (Nmap/Metasploit)
🔑 Get more tokens by downloading our Free Network Monitor Agent

🔵 HugLLM – Open-source models (≈8B params):

2x more tokens than TurboLLM
AI-powered log analysis
🌐 Runs on Hugging Face Inference API

💡 Example AI Commands to Test:

"Give me info on my websites SSL certificate"
"Check if my server is using quantum safe encyption for communication"
"Run a quick Nmap vulnerability test"

Granite-3.2-2B-Instruct

Model Summary: Granite-3.2-2B-Instruct is an 2-billion-parameter, long-context AI model fine-tuned for thinking capabilities. Built on top of Granite-3.1-2B-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
Release Date: February 26th, 2025
License: Apache 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-3.2-2B-Instruct model.

Install the following libraries:

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.

from transformers import AutoModelForCausalLM, AutoTokenizer, set_seed
import torch

model_path="ibm-granite/granite-3.2-2b-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

Here is my thought process:

1. First, let's understand the composition of the initial 10 liters of 30% acid solution:
   - Acid content = 30% of 10 liters = 0.30 * 10 = 3 liters

2. We want to end up with a 50% acid solution. Let's denote the volume of the 70% acid solution to be added as 'x' liters.

3. The amount of acid in the final mixture (50% solution) should equal the initial acid content plus the acid from the added 70% solution.
   - Total acid in final mixture = 0.50 * (10 + x)

4. The equation representing the total acid content is:
   3 (from initial solution) + 0.70 * x (from added solution) = 0.50 * (10 + x)

5. Now, we solve for 'x':
   3 + 0.70x = 5 + 0.50x
   0.70x - 0.50x = 5 - 3
   0.20x = 2
   x = 2 / 0.20
   x = 10 liters

6. Therefore, 10 liters of a 70% acid solution must be added to the initial 10 liters of 30% acid solution to achieve a 50% acid mixture.

Here is my response:

To solve this problem, we need to determine how much of a 70% acid solution must be added to a 10-liter solution that is already 30% acid to create a new mixture that is 50% acid. Here's how to calculate it:

1. **Initial Acid Content**:
   - The initial 10-liter solution contains 3 liters of acid (since 30% of 10 liters).

2. **Desired Final Acid Content**:
   - We want the final mixture to be 50% acid.

3. **Equation Setup**:
   - Let 'x' be the volume (in liters) of the 70% acid solution to be added.
   - The equation representing the total acid content in the final mixture (which is 10 liters from the initial solution plus 'x' liters of the added solution) should equal 50% of the total volume (10 + x).
   - This gives us: 3 (acid from initial solution) + 0.70x (acid from added solution) = 0.50(10 + x)

4. **Solving the Equation**:
   - First, simplify the right side of the equation: 0.50(10 + x) = 5 + 0.50x
   - Now, the equation is: 3 + 0.70x = 5 + 0.50x
   - Subtract 0.50x from both sides: 0.20x = 2
   - Divide both sides by 0.20: x = 2 / 0.20
   - x = 10 liters

5. **Conclusion**:
   - To achieve a 50% acid mixture from the initial 30% solution, you need to add 10 liters of a 70% acid solution.

So, the final answer is that 10 liters of a 70% acid solution must be added to the initial 10 liters of 30% acid solution.

thinking=False

To solve this problem, we'll use the concept of volume and concentration. Let's denote the amount of 70% acid solution we need to add as "x" liters.

First, let's find out how much acid is in the initial 10-liter solution:

Acid in initial solution = 30% of 10 liters = 0.30 * 10 = 3 liters

Now, we want to end up with a 50% acid solution in a total volume of (10 + x) liters. Let's denote the final volume as V.

Final acid concentration = 50%
Final acid amount = 50% of V = 0.50 * V

We know the initial acid amount and the final acid amount, so we can set up an equation:

Initial acid amount + Acid from added solution = Final acid amount
3 liters + (70% of x) = 0.50 * (10 + x)

Now, let's solve for x:

0.70x + 3 = 0.50 * 10 + 0.50x
0.70x - 0.50x = 0.50 * 10 - 3
0.20x = 5 - 3
0.20x = 2
x = 2 / 0.20
x = 10 liters

So, you need to add 10 liters of a 70% acid solution to the initial 10-liter 30% acid solution to achieve a 50% acid mixture.

Evaluation Results:

Models	ArenaHard	Alpaca-Eval-2	MMLU	PopQA	TruthfulQA	BigBenchHard	DROP	GSM8K	HumanEval	HumanEval+	IFEval	AttaQ
Llama-3.1-8B-Instruct	36.43	27.22	69.15	28.79	52.79	72.66	61.48	83.24	85.32	80.15	79.10	83.43
DeepSeek-R1-Distill-Llama-8B	17.17	21.85	45.80	13.25	47.43	65.71	44.46	72.18	67.54	62.91	66.50	42.87
Qwen-2.5-7B-Instruct	25.44	30.34	74.30	18.12	63.06	70.40	54.71	84.46	93.35	89.91	74.90	81.90
DeepSeek-R1-Distill-Qwen-7B	10.36	15.35	50.72	9.94	47.14	65.04	42.76	78.47	79.89	78.43	59.10	42.45
Granite-3.1-8B-Instruct	37.58	30.34	66.77	28.7	65.84	68.55	50.78	79.15	89.63	85.79	73.20	85.73
Granite-3.1-2B-Instruct	23.3	27.17	57.11	20.55	59.79	54.46	18.68	67.55	79.45	75.26	63.59	84.7
Granite-3.2-8B-Instruct	55.25	61.19	66.79	28.04	66.92	64.77	50.95	81.65	89.35	85.72	74.31	85.42
Granite-3.2-2B-Instruct	24.86	34.51	57.18	20.56	59.8	52.27	21.12	67.02	80.13	73.39	61.55	83.23

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.

Infrastructure: We train Granite-3.2-2B-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-3.2-2B-Instruct builds upon Granite-3.1-2B-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-3.1-2B-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