CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.granite / granite-guardian-3.3-8b-GGUF
From: ibm-granite <huggingface.co/ibm-granite>Newsgroups: alt.freeweights.graniteSubject:

granite-guardian-3.3-8b-GGUF

Date: 2026-11-15Commit: 8c87479Signed: 2DC28CC7B26A283B ✓

Text generation model. Gguf weights, 42.5 GB in all. Published by ibm-granite under Apache-2.0.

granite42.5GBgranite-guardian-3.3-8b-GGUFggufpermissive
FactsParamsnot statedSize42.5 GBFormatsggufTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get ibm-granite/granite-guardian-3.3-8b-GGUF
# manifest sha256 573d408f8dc6… · 42.5 GB · 7 files
$ fw verify ./granite-guardian-3.3-8b-GGUF ibm-granite/granite-guardian-3.3-8b-GGUF
From sourceHosted (signed)ibm-granite/granite-guardian-3.3-8b-GGUFLast check: 2026-11-15 05:03 UTC
Run at homeGet help

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

Quantized of granite-guardian-3.3-8b.

Works with

Run14Convert1Evaluate13Scan12Apps58

Convert with

ggml
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
42.5 GB
Weights
4.94 GB (smallest of 5 GGUF variants)
Parameters
not stated
Formats
gguf
Task
text generation
License
Apache-2.0 (permissive)
Files
7, each with a sha256
Publisher
ibm-granite
Added
2026-11-15
Section
alt.freeweights.granite
Lineage

Original release from the publisher.

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

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 05:03 UTCpassed

Model card

From the publisher at commit 8c87479. Shown as plain text with links; images open at the publisher.

Note. This repository contains models that have been converted to the GGUF format with various quantizations from an IBM Granite base model.

Please reference the base model's full model card here: https://huggingface.co/ibm-granite/granite-guardian-3.3-8b

granite-guardian-3.3-8b-GGUF#

Model Summary: Granite Guardian 3.3 8b is a specialized Granite 3.3 8B model designed to judge if the input prompts and the output responses of an LLM based system meet specified criteria. The model comes pre-baked with certain criteria including but not limited to: jailbreak attempts, profanity, and hallucinations related to tool calls and retrieval augmented generation in agent-based systems. Additionally, the model also allows users to bring their own criteria and tailor the judging behavior to specific use-cases.

This version of Granite Guardian is a hybrid thinking model that allows the user to operate in thinking or non-thinking model. In thinking mode, the model produces detailed reasoning traces though <think> ... </think>and <score> ... </score> tags. In non-thinking mode, the model only produces the judgement score though the <score> ... </score> tags.

It is trained on unique data comprising human annotations and synthetic data informed by internal red-teaming. It outperforms other open-source models in the same space on standard benchmarks.

Files

7 files · 42.5 GBWeights 4.94 GB (smallest of 5 GGUF variants). Sizes and sha256 from the signed manifest.
Hide all 7 files with their sha256
FileSizesha256
.gitattributes1.87 KB2dc5f55e604f026ecea5c1b3bd5630d95aa917d6817ab88e79e02e65b99ad947
README.md2.12 KBb0899065c211f10d48ed2acb41df9ee836ccc34996216b187bfc0b35e7c03c46
granite-guardian-3.3-8b-Q4_K_M.gguf4.94 GBb4fa861b5163373413d9659c22e344e6206baad824ead17226b2058e54d14587
granite-guardian-3.3-8b-Q5_K_M.gguf5.80 GBd7a29778234185881e126e07cb72d97c0215310e239c77a76819153f5e0c842f
granite-guardian-3.3-8b-Q6_K.gguf6.71 GB4b4da519efeaa6681d700a437b16a263f813376151c2a2a4a8dd7bb03623e34f
granite-guardian-3.3-8b-Q8_0.gguf8.68 GB356fc80d343a699a3d12316de161d4341ee2d11f7057123dabb158804e876bc5
granite-guardian-3.3-8b-f16.gguf16.3 GB656b4f3ad18f34dbcb56c42a08bdd1ddbcfa295e71bc31c74430db1d5f6f2e31
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
8c87479a2d pinned now2026-11-15 05:03 UTC7 files · 42.5 GB

Use it

$ fw get ibm-granite/granite-guardian-3.3-8b-GGUF
# manifest sha256 573d408f8dc6… · 42.5 GB · 7 files
$ fw verify ./granite-guardian-3.3-8b-GGUF ibm-granite/granite-guardian-3.3-8b-GGUF
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-guardian-3.3-8b-GGUF.json --dir ./granite-guardian-3.3-8b-GGUF $ python3 fw.py verify ./granite-guardian-3.3-8b-GGUF ./ibm-granite__granite-guardian-3.3-8b-GGUF.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ibm-granite/granite-guardian-3.3-8b-GGUF --revision 8c87479a2dc329e4e362a6e5dda7e7de3e0372b2 --local-dir ./granite-guardian-3.3-8b-GGUF
llama.cppDownload one GGUF variant (granite-guardian-3.3-8b-Q4_K_M, 4.94 GB), then serve it.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ibm-granite/granite-guardian-3.3-8b-GGUF --include "granite-guardian-3.3-8b-Q4_K_M*" --local-dir ./granite-guardian-3.3-8b-GGUF $ llama-server -m ./granite-guardian-3.3-8b-GGUF/granite-guardian-3.3-8b-Q4_K_M.gguf
OllamaMake an Ollama model from the downloaded file.
$ printf 'FROM ./granite-guardian-3.3-8b-GGUF/granite-guardian-3.3-8b-Q4_K_M.gguf\n' > Modelfile $ ollama create granite-guardian-3.3-8b-gguf -f Modelfile
Run at home

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
b0899065c211f10d48ed2acb41df9ee836ccc34996216b187bfc0b35e7c03c46
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-guardian-3.3-8b-GGUFDate: 2026-11-15Commit: 8c87479Signed: 2DC28CC7B26A283B ✓
Upstream
ibm-granite/granite-guardian-3.3-8b-GGUF
Pinned commit
8c87479a2dc329e4e362a6e5dda7e7de3e0372b2
Manifest
granite-guardian-3.3-8b-GGUF.json · .minisig
Manifest sha256
573d408f8dc64de14a586a9b63790809acda97db37889f1527d7ab34cabaea96
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:03 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/ibm-granite/granite-guardian-3.3-8b-GGUF.json $ curl -O https://freeweights.allternit.com/manifests/ibm-granite/granite-guardian-3.3-8b-GGUF.json.minisig $ minisign -Vm granite-guardian-3.3-8b-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-guardian-3.3-8b · 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 ibm-granite/granite-guardian-3.3-8b-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-guardian-3.3-8b-GGUF.json. Provenance. Takedown history: none.
Source
huggingface.co/ibm-granite/granite-guardian-3.3-8b-GGUF

Related models

All of alt.freeweights.granite →
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