alt.freeweights.granite / granite-3.3-8b-instruct
From: ibm-granite <huggingface.co/ibm-granite>Newsgroups: alt.freeweights.graniteSubject:

granite-3.3-8b-instruct

Date: 2026-11-14Commit: 51dd4bcSigned: 2DC28CC7B26A283B ✓

Text generation model with 8.2B parameters. Safetensors weights, 16.3 GB in all. Published by ibm-granite under Apache-2.0.

8.2B params16.3GBgranite-3.3-8b-instructsafetensorspermissive
FactsParams8.2BSize16.3 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get ibm-granite/granite-3.3-8b-instruct
# manifest sha256 d7f3cc1e432f… · 16.3 GB · 15 files
$ fw verify ./granite-3.3-8b-instruct ibm-granite/granite-3.3-8b-instruct
From sourceHosted (signed)ibm-granite/granite-3.3-8b-instructLast check: 2026-11-14 21:16 UTC

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Fine-tune of granite-3.3-8b-base.

Works with

Overview

Size
16.3 GB
Weights
16.3 GB (safetensors)
Parameters
8.2B
Formats
safetensors
Task
text generation
License
Apache-2.0 (permissive)
Files
15, each with a sha256
Publisher
ibm-granite
Added
2026-11-14
Section
alt.freeweights.granite
Lineage

Original release from the publisher.

Base model: ibm-granite/granite-3.3-8b-base

Where these bytes come from
Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-14 21:16 UTCpassed

Model card

From the publisher at commit 51dd4bc. Shown as plain text with links; images open at the publisher.

Granite-3.3-8B-Instruct#

Model Summary: Granite-3.3-8B-Instruct is a 8-billion parameter 128K context length language model fine-tuned for improved reasoning and instruction-following capabilities. Built on top of Granite-3.3-8B-Base, the model delivers significant gains on benchmarks for measuring generic performance including AlpacaEval-2.0 and Arena-Hard, and improvements in mathematics, coding, and instruction following. It supports structured reasoning through \<think\>\<\/think\> and \<response\>\<\/response\> tags, providing clear separation between internal thoughts and final outputs. The model has been trained on a carefully balanced combination of permissively licensed data and curated synthetic tasks.

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-3.3-8B-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-3.3-8b-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":"Redesign a common household item to make it more sustainable and user-friendly. Explain the changes and their benefits."}]

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
<think>To address this prompt, I'll focus on redesigning a common household item: the plastic water bottle. The goal is to make it more sustainable and user-friendly. Here are the proposed changes and their benefits:

1. **Material**: Replace plastic with biodegradable or recyclable materials like glass or plant-based plastics (PLA).
2. **Design**: Introduce a modular design for easy refilling and cleaning.
3. **Functionality**: Incorporate a built-in water filter for purification.
4. **Durability**: Enhance the bottle's lifespan through robust construction.
5. **User-friendliness**: Simplify the cap mechanism for easy opening and closing.

These changes would significantly reduce plastic waste, promote recycling, ensure access to clean drinking water, and enhance the overall user experience.

Now, I will detail each change and its benefits in a structured format.</think>

<response>### Redesign of the Plastic Water Bottle for Sustainability and User-Friendliness

#### 1. Material: Biodegradable or Recyclable Alternatives

**Change**: Transition from traditional PET plastic to glass or plant-based plastics (Polylactic Acid - PLA).

**Benefits**:
- **Sustainability**: Glass and PLA are biodegradable or highly recyclable, drastically reducing plastic pollution.
- **Health**: Unlike PET, these materials do not leach chemicals into the water, ensuring safer consumption.

#### 2. Modular Design for Easy Refilling and Cleaning

**Change**: Implement a detachable, interchangeable inner liner within a reusable outer casing.

**Benefits**:
- **User-Friendliness**: Users can easily remove the inner liner for thorough cleaning, reducing the risk of bacterial growth.
- **Sustainability**: The outer casing remains intact, encouraging reuse, while the inner liner can be replaced or recycled when worn out.

#### 3. Built-in Water Filter

**Change**: Integrate a removable, replaceable water filter into the bottle cap.

**Benefits**:
- **Accessibility**: Provides clean drinking water directly from any source (tap, river, etc.), eliminating the need for additional filtration devices.
- **Health**: Removes contaminants, bacteria, and impurities, ensuring safe hydration.
- **Sustainability**: Reduces the use of single-use plastic water bottles by offering a purification solution within a reusable container.

#### 4. Enhanced Durability

**Change**: Use high-quality, durable materials and robust construction techniques for both the outer casing and inner liner.

**Benefits**:
- **Longevity**: A more robust design increases the bottle's lifespan, reducing the frequency of replacements.
- **Cost-effectiveness**: Although the initial cost might be higher, the long-term savings from reduced replacements make it economical.
- **Sustainability**: Less frequent disposal means lower environmental impact.

#### 5. Simplified Cap Mechanism

**Change**: Adopt a one-touch, easy-to-open and close cap design, possibly inspired by sports bottle caps.

**Benefits**:
- **User-Friendliness**: Especially beneficial for children, elderly, or those with limited hand dexterity.
- **Convenience**: Quick access to water encourages more frequent hydration, promoting healthier habits.

### Conclusion

This redesigned water bottle addresses key sustainability concerns by minimizing plastic use and waste, while also enhancing user-friendliness through improved functionality, durability, and accessibility. By integrating biodegradable materials, a modular design, a built-in filter, robust construction, and a simple cap mechanism, the bottle not only reduces environmental footprint but also offers a superior user experience.</response>
  • thinking=False
Item for Redesign: Plastic Bottle (e.g., water or beverage bottle)

Redesign Concept: Eco-Friendly, Modular, and Multi-Functional Reusable Bottle

Changes:

1. Material: Replace the conventional plastic with food-grade, BPA-free, and recyclable materials such as stainless steel or glass. These materials are durable, non-toxic, and have a longer lifespan, reducing waste.

2. Modular Design: Introduce a modular design that allows users to customize their bottle according to their needs. This could include interchangeable caps, mouthpiece sizes, and carrying loops. Users can purchase additional modules as needed, promoting a more sustainable approach by reducing the need to buy an entirely new bottle for different purposes.

3. Integrated Filter: Incorporate a built-in, washable, and reusable filter that can remove impurities and improve the taste of water. This eliminates the need for single-use disposable filters or bottled water, further reducing plastic waste.

4. Smart Cap: Develop a smart cap with a built-in digital display and temperature sensor. This feature allows users to track their daily water intake, set hydration goals, and monitor the temperature of their beverage. The smart cap can be synced with a mobile app for additional functionality, such as reminders and progress tracking.

5. Easy-to-Clean Design: Ensure the bottle has a wide mouth and smooth interior surfaces for easy cleaning. Include a brush for hard-to-reach areas, making maintenance simple and encouraging regular use.

6. Collapsible Structure: Implement a collapsible design that reduces the bottle's volume when not in use, making it more portable and convenient for storage.

Benefits:

1. Sustainability: By using recyclable materials and reducing plastic waste, this redesigned bottle significantly contributes to a more sustainable lifestyle. The modular design and reusable filter also minimize single-use plastic consumption.

2. User-Friendly: The smart cap, easy-to-clean design, and collapsible structure make the bottle convenient and user-friendly. Users can customize their bottle to suit their needs, ensuring a better overall experience.

3. Healthier Option: Using food-grade, BPA-free materials and an integrated filter ensures that the beverages consumed are free from harmful chemicals and impurities, promoting a healthier lifestyle.

4. Cost-Effective: Although the initial investment might be higher, the long-term savings from reduced purchases of single-use plastic bottles and disposable filters make this reusable bottle a cost-effective choice.

5. Encourages Hydration: The smart cap's features, such as hydration tracking and temperature monitoring, can motivate users to stay hydrated and develop healthier habits.

By redesigning a common household item like the plastic bottle, we can create a more sustainable, user-friendly, and health-conscious alternative that benefits both individuals and the environment.

Evaluation Results:

Comparison with different models over various benchmarks1. Scores of AlpacaEval-2.0 and Arena-Hard are calculated with thinking=True

| Models | Arena-Hard | AlpacaEval-2.0 | MMLU | PopQA | TruthfulQA | BigBenchHard2 | DROP3 | GSM8K | HumanEval | HumanEval+ | IFEval | AttaQ

| Granite-3.1-2B-Instruct | 23.3 | 27.17 | 57.11 | 20.55 | 59.79 | 61.82 | 20.99 | 67.55 | 79.45 | 75.26 | 63.59 | 84.7

| Granite-3.2-2B-Instruct | 24.86 | 34.51 | 57.18 | 20.56 | 59.8 | 61.39 | 23.84 | 67.02 | 80.13 | 73.39 | 61.55 | 83.23

| Granite-3.3-2B-Instruct | 28.86 | 43.45 | 55.88 | 18.4 | 58.97 | 63.91 | 44.33 | 72.48 | 80.51 | 75.68 | 65.8 | 87.47

| Llama-3.1-8B-Instruct | 36.43 | 27.22 | 69.15 | 28.79 | 52.79 | 73.43 | 71.23 | 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 | 67.39 | 49.73 | 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 | 69.19 | 64.06 | 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 | 67.38 | 51.78 | 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 | 69.87 | 58.57 | 79.15 | 89.63 | 85.79 | 73.20 | 85.73

| Granite-3.2-8B-Instruct | 55.25 | 61.19 | 66.79 | 28.04 | 66.92 | 71.86 | 58.29 | 81.65 | 89.35 | 85.72 | 74.31 | 84.7

| Granite-3.3-8B-Instruct | 57.56 | 62.68 | 65.54 | 26.17 | 66.86 | 69.13 | 59.36 | 80.89 | 89.73 | 86.09 | 74.82 | 88.5

Math Benchmarks

| Models | AIME24 | MATH-500

| Granite-3.1-2B-Instruct | 0.89 | 35.07

| Granite-3.2-2B-Instruct | 0.89 | 35.54

| Granite-3.3-2B-Instruct | 3.28 | 58.09

| Granite-3.1-8B-Instruct | 1.97 | 48.73

| Granite-3.2-8B-Instruct | 2.43 | 52.8

| Granite-3.3-8B-Instruct | 8.12 | 69.02

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-3.3-8B-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-3.3-8B-Instruct builds upon Granite-3.3-8B-Base, 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-3.3-8B-Base remain relevant.

Resources

1 Evaluated using OLMES (except AttaQ and Arena-Hard scores)

2 Added regex for more efficient asnwer extraction.

3 Modified the implementation to handle some of the issues mentioned here

Files

15 files · 16.3 GBWeights 16.3 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 15 files with their sha256
FileSizesha256
.gitattributes1.52 KB11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
README.md27.6 KB827b04e8019ae72397d7303e8b30f315d4b8f5d1cd18f9f4e3f0d7808f069a35
added_tokens.json207 Bbb33d55934aa82d29cc62f3d19cdbc60f315763f6ccee21bdfd8b3bde2f33d3b
config.json790 B1313edf0d39dcf7ed35a072d341ec11b516c12acc4267cfb6d248c6bdcdddcb7
generation_config.json132 B9c95e80167f08fbeb1feba239e0749507c25d18ffab43ffa10887821eed21c38
merges.txt442 KB303127a244b0078878156c17229f36d11b7a3a3f8e47b7cfdbb304ff46be5030
model-00001-of-00004.safetensors4.97 GBb309f7b9e116fafc27c1100629bfcccbcebdab18a4bf7df7accfa728260dc57e
model-00002-of-00004.safetensors4.99 GBf2e40f157f0139e4b67bbaa4b10efa351162c062771cb543b143c6916a687266
model-00003-of-00004.safetensors4.97 GB5cf5203a027b7055c995a9d4bdb3a4c9dd44849ae6c9eefa6a16852a816bea76
model-00004-of-00004.safetensors1.41 GB76ac0c0dbd790a1e003d2fc098a297bfe82a422c129046e9d4e67e6ed3d820f0
model.safetensors.index.json29.8 KBc3a88218300666c35343b129857d4e8583ee1b15bf68d90ab976f51744560379
special_tokens_map.json801 B21ce694081bb9ae1bd4bc64549e72e0799ebb74705e6b650e3585d85b71ebdc1
tokenizer.json3.48 MB91168e938f05796aa6dcca7e485e4b30ab52785320c7a6391ecef86e6c84681e
tokenizer_config.json9.93 KBf65a6a5a911424c85f157c40cfbdf06e025814c755480ba2e998d7fba1178664
vocab.json777 KB80ab859339a2525fdfbda14bc39df02dffb824aefdaf86426217bbb146d17e01
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
51dd4bc2ad pinned now manifest updated, same commit2026-11-14 21:16 UTC15 files · 16.3 GB
51dd4bc2ad2026-11-14 21:16 UTC15 files · 16.3 GB

Use it

$ fw get ibm-granite/granite-3.3-8b-instruct
# manifest sha256 d7f3cc1e432f… · 16.3 GB · 15 files
$ fw verify ./granite-3.3-8b-instruct ibm-granite/granite-3.3-8b-instruct
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/ibm-granite/granite-3.3-8b-instruct.json --dir ./granite-3.3-8b-instruct $ python3 fw.py verify ./granite-3.3-8b-instruct ./ibm-granite__granite-3.3-8b-instruct.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ibm-granite/granite-3.3-8b-instruct --revision 51dd4bc2ade4059a6bd87649d68aa11e4fb2529b --local-dir ./granite-3.3-8b-instruct
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForCausalLM, AutoTokenizer tok = AutoTokenizer.from_pretrained("ibm-granite/granite-3.3-8b-instruct", revision="51dd4bc2ade4059a6bd87649d68aa11e4fb2529b") model = AutoModelForCausalLM.from_pretrained("ibm-granite/granite-3.3-8b-instruct", revision="51dd4bc2ade4059a6bd87649d68aa11e4fb2529b", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve ibm-granite/granite-3.3-8b-instruct --revision 51dd4bc2ade4059a6bd87649d68aa11e4fb2529b

License

Name
Apache License 2.0
Id
Apache-2.0
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-14
Text in
README.md
Text sha256
827b04e8019ae72397d7303e8b30f315d4b8f5d1cd18f9f4e3f0d7808f069a35
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: ibm-granite <huggingface.co/ibm-granite>Newsgroups: alt.freeweights.graniteSubject: granite-3.3-8b-instructDate: 2026-11-14Commit: 51dd4bcSigned: 2DC28CC7B26A283B ✓
Upstream
ibm-granite/granite-3.3-8b-instruct
Pinned commit
51dd4bc2ade4059a6bd87649d68aa11e4fb2529b
Manifest
granite-3.3-8b-instruct.json · .minisig
Manifest sha256
d7f3cc1e432f6a70256b454de938bdd6368be9933cea6d87cf6d66cc96a00b98
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-14 21:16 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/ibm-granite/granite-3.3-8b-instruct.json $ curl -O https://freeweights.allternit.com/manifests/ibm-granite/granite-3.3-8b-instruct.json.minisig $ minisign -Vm granite-3.3-8b-instruct.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq $ shasum -a 256 <file> # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

Parent

ibm-granite/granite-3.3-8b-base · this model is a finetune of it

10 models in the catalog name this one as their parent.

Fine-tunes
5
Quantizations
5
Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ibm-granite/granite-3.3-8b-instruct
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. granite-3.3-8b-instruct.json. Provenance. Takedown history: none.

Variants

5 quantized or adapter builds of granite-3.3-8b-instruct. Each has its own license check and page.

From: ibm-granite <huggingface.co/ibm-granite>Subject: GneissWeb.7B_ablation_model_on_350B_FineWeb.Edu.seed1
From: ibm-granite <huggingface.co/ibm-granite>Subject: GneissWeb.7B_ablation_model_on_350B_FineWeb.Edu.seed2
From: ibm-granite <huggingface.co/ibm-granite>Subject: GneissWeb.7B_ablation_model_on_350B_FineWeb.Edu.seed3
From: ibm-granite <huggingface.co/ibm-granite>Subject: GneissWeb.7B_ablation_model_on_350B_FineWeb.seed1
From: ibm-granite <huggingface.co/ibm-granite>Subject: GneissWeb.7B_ablation_model_on_350B_FineWeb.seed2
From: ibm-granite <huggingface.co/ibm-granite>Subject: GneissWeb.7B_ablation_model_on_350B_FineWeb.seed3