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

granite-3.3-8b-instruct-GGUF

Date: 2026-11-15Commit: 42f7360Signed: 2DC28CC7B26A283B ✓

Text generation model. Gguf weights, 125 GB in all. Published by unsloth under Apache-2.0.

granite125GBgranite-3.3-8b-instruct-GGUFggufpermissive
FactsParamsnot statedSize125 GBFormatsggufTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get unsloth/granite-3.3-8b-instruct-GGUF
# manifest sha256 3f5d98050eea… · 125 GB · 29 files
$ fw verify ./granite-3.3-8b-instruct-GGUF unsloth/granite-3.3-8b-instruct-GGUF
From sourceHosted (signed)unsloth/granite-3.3-8b-instruct-GGUFLast check: 2026-11-15 05:00 UTC

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

Quantized of granite-3.3-8b-instruct.

Works with

Convert with

Overview

Size
125 GB
Weights
1.93 GB (smallest of 25 GGUF variants)
Parameters
not stated
Formats
gguf
Task
text generation
License
Apache-2.0 (permissive)
Files
29, each with a sha256
Publisher
unsloth
Added
2026-11-15
Section
alt.freeweights.granite
Lineage

Original release from the publisher.

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

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.co2026-11-15 05:00 UTCpassed

Model card

From the publisher at commit 42f7360. 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 supprts 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

29 files · 125 GBWeights 1.93 GB (smallest of 25 GGUF variants). Sizes and sha256 from the signed manifest.
Show all 29 files with their sha256
FileSizesha256
.gitattributes3.40 KBd579f6aa5dc100cf4dd219475c77d4f613c36b2f7d430fccc271612b8e7f630f
README.md27.6 KBd04c95a62320f592726c99499bae3078485af6bf8892220a56f39b487069e1b2
config.json820 B1e59ad2e1171d26b0282628224d4e1b390664d6df90e9fd50a8c62d2ce568696
granite-3.3-8b-instruct-BF16.gguf16.3 GBdff1ccae274a90e83833c07ac69b4e6fa296c8d6dc38223f55de830db3371a5e
granite-3.3-8b-instruct-IQ4_NL.gguf4.67 GB2a63bd527a77d776fcbfb279dedee60ec0256128df23819629ab2d558274b4ee
granite-3.3-8b-instruct-IQ4_XS.gguf4.43 GBe0f00ebb63e74d2485c74b185eef4eb530aa77cd3b8109a0c3d4b9045c52d5e3
granite-3.3-8b-instruct-Q2_K.gguf3.10 GB20e7873a30f5b4f21a006c228e6b0735f8ca6c1a96892442387cbe5bb62d8944
granite-3.3-8b-instruct-Q2_K_L.gguf3.10 GB20e7873a30f5b4f21a006c228e6b0735f8ca6c1a96892442387cbe5bb62d8944
granite-3.3-8b-instruct-Q3_K_M.gguf4.00 GBf659907b531ccf188d0d39eb7e0da529bf24ddbdaf35637ea22b4117bc14d431
granite-3.3-8b-instruct-Q3_K_S.gguf3.59 GB9da0a51f1489ea7c94cbb37d3bb648a8f14f188ff19c1072265666539d4284ce
granite-3.3-8b-instruct-Q4_0.gguf4.67 GBca876732f4378806c67350b13df8e9d542dbd958695edd1fa78a222cb24a6bc8
granite-3.3-8b-instruct-Q4_1.gguf5.15 GB1992efe8b82d03782b8bc25d181277f47e9d2e4592e8388fb33a45c66d2dd16f
granite-3.3-8b-instruct-Q4_K_M.gguf4.94 GB7057b01e68af6819e5273c75cc2d948d48eeaa750962e5eebb4ecf916a910f33
granite-3.3-8b-instruct-Q4_K_S.gguf4.69 GB2fa13551d4e82f1a7a809b32953baeb7000bb7f9ee3523e3b5fcab4d304a0748
granite-3.3-8b-instruct-Q5_K_M.gguf5.80 GB31c4c864faf0c0a52c3970d36729f30b83e4eb42408883f8ab7e77718c4fceb4
granite-3.3-8b-instruct-Q5_K_S.gguf5.65 GBcf55a1810a8511c35c2f277960c27e3d8965aa5c1ddff2d57d1943c0a98c34bb
granite-3.3-8b-instruct-Q6_K.gguf6.71 GB9be271d5192a0a9a017c0cb9d3890c02c0089656a8f7b36dd2c48d8450eee906
granite-3.3-8b-instruct-UD-IQ1_M.gguf2.07 GB50c767fca75ebb64d2a8e39e324be1d8e71800622a931d4b9dd5f54d95640372
granite-3.3-8b-instruct-UD-IQ1_S.gguf1.93 GB773dcbca91a530be7b34cff6af73e62da19a05ef3718562a4db87228a24f6e3d
granite-3.3-8b-instruct-UD-IQ2_M.gguf2.89 GB90586f54c8b306125dbb51c324d266dde7a883fe0f42ca998ecf355539d9cd3e
granite-3.3-8b-instruct-UD-IQ2_XXS.gguf2.32 GB9323ef9a3e01dafb82a78b22c49ad40331f2c2826eacd65c15611878c704b3f5
granite-3.3-8b-instruct-UD-IQ3_XXS.gguf3.24 GB0d84f6263fc9bb80f9546a54f24e2711a2bda21e16385050de1f26789a6e020f
granite-3.3-8b-instruct-UD-Q2_K_XL.gguf3.18 GBe5273c35ee4cc8e9b9ca515781065b312fbef9d4777cd74899ae5f29320d3164
granite-3.3-8b-instruct-UD-Q3_K_XL.gguf4.10 GB25d9c15b6549ae1aab10d3365578ff73b4aaff191060a7b132b2dd58170d4482
granite-3.3-8b-instruct-UD-Q4_K_XL.gguf5.04 GB34fc9c158463ddfcbb71c54b3781735881454b7a4a306fdb2a2f4a28cf19bf75
granite-3.3-8b-instruct-UD-Q5_K_XL.gguf5.82 GB1faa62977f46ee86d3dc1957fcdd57825bce37273d346cae15352fadd3de6583
granite-3.3-8b-instruct-UD-Q6_K_XL.gguf7.25 GBb026cf0139d9050f6035b2e1b198b191ce52e2ecca673abbf8ad38bb336dca06
granite-3.3-8b-instruct-UD-Q8_K_XL.gguf9.87 GB8e25789895723d433da635fd07f90825efb9d2982e553cb2df741640508fce05
imatrix_unsloth.dat5.99 MB56f9b3d72abab26d6073342f9283d1382008583074bbd88ef40f0a5da4b241df
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
42f7360b07 pinned now2026-11-15 05:00 UTC29 files · 125 GB

Use it

$ fw get unsloth/granite-3.3-8b-instruct-GGUF
# manifest sha256 3f5d98050eea… · 125 GB · 29 files
$ fw verify ./granite-3.3-8b-instruct-GGUF unsloth/granite-3.3-8b-instruct-GGUF
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/unsloth/granite-3.3-8b-instruct-GGUF.json --dir ./granite-3.3-8b-instruct-GGUF $ python3 fw.py verify ./granite-3.3-8b-instruct-GGUF ./unsloth__granite-3.3-8b-instruct-GGUF.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download unsloth/granite-3.3-8b-instruct-GGUF --revision 42f7360b079adc00d9542b943b7affdefa0a5adf --local-dir ./granite-3.3-8b-instruct-GGUF
llama.cppDownload one GGUF variant (granite-3.3-8b-instruct-UD-IQ1_S, 1.93 GB), then serve it.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download unsloth/granite-3.3-8b-instruct-GGUF --include "granite-3.3-8b-instruct-UD-IQ1_S*" --local-dir ./granite-3.3-8b-instruct-GGUF $ llama-server -m ./granite-3.3-8b-instruct-GGUF/granite-3.3-8b-instruct-UD-IQ1_S.gguf
OllamaMake an Ollama model from the downloaded file.
$ printf 'FROM ./granite-3.3-8b-instruct-GGUF/granite-3.3-8b-instruct-UD-IQ1_S.gguf\n' > Modelfile $ ollama create granite-3.3-8b-instruct-gguf -f Modelfile

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. 2026-11-15
Text in
README.md
Text sha256
d04c95a62320f592726c99499bae3078485af6bf8892220a56f39b487069e1b2
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: unsloth <huggingface.co/unsloth>Newsgroups: alt.freeweights.graniteSubject: granite-3.3-8b-instruct-GGUFDate: 2026-11-15Commit: 42f7360Signed: 2DC28CC7B26A283B ✓
Upstream
unsloth/granite-3.3-8b-instruct-GGUF
Pinned commit
42f7360b079adc00d9542b943b7affdefa0a5adf
Manifest
granite-3.3-8b-instruct-GGUF.json · .minisig
Manifest sha256
3f5d98050eea2f032e6f5342fff2eee17544cd0ace16b953a57bbc8d8795c593
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:00 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/unsloth/granite-3.3-8b-instruct-GGUF.json $ curl -O https://freeweights.allternit.com/manifests/unsloth/granite-3.3-8b-instruct-GGUF.json.minisig $ minisign -Vm granite-3.3-8b-instruct-GGUF.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-instruct · this model is a quantization of it

No model in the catalog names this one as its parent.

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download unsloth/granite-3.3-8b-instruct-GGUF
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-GGUF.json. Provenance. Takedown history: none.
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