CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.granite / granite-guardian-4.1-8b-GGUF
From: ibm-granite <huggingface.co/ibm-granite>Newsgroups: alt.freeweights.graniteSubject:

granite-guardian-4.1-8b-GGUF

Date: 2026-11-15Commit: bc78f09Signed: 2DC28CC7B26A283B ✓

Text generation model. Gguf weights, 92.3 GB in all. Published by ibm-granite under Apache-2.0.

granite92.3GBgranite-guardian-4.1-8b-GGUFggufpermissive
FactsParamsnot statedSize92.3 GBFormatsggufTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get ibm-granite/granite-guardian-4.1-8b-GGUF
# manifest sha256 140fd55fb98d… · 92.3 GB · 17 files
$ fw verify ./granite-guardian-4.1-8b-GGUF ibm-granite/granite-guardian-4.1-8b-GGUF
From sourceHosted (signed)ibm-granite/granite-guardian-4.1-8b-GGUFLast check: 2026-11-15 04:54 UTC
Run at homeGet help

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

Quantized of granite-guardian-4.1-8b.

Works with

Run14Convert1Evaluate13Scan12Apps58

Convert with

ggml
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
92.3 GB
Weights
3.28 GB (smallest of 15 GGUF variants)
Parameters
not stated
Formats
gguf
Task
text generation
License
Apache-2.0 (permissive)
Files
17, 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-4.1-8b

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 04:54 UTCpassed

Model card

From the publisher at commit bc78f09. 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-4.1-8b

Granite Guardian 4.1 8B (GGUF)#

Model Summary#

Granite Guardian 4.1 8B is a specialized safety model fine-tuned from ibm-granite/granite-4.1-8b, 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 mode. In thinking mode, the model produces detailed reasoning traces through <think> ... </think> and <score> ... </score> tags. In non-thinking mode, the model only produces the judgement score through 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

17 files · 92.3 GBWeights 3.28 GB (smallest of 15 GGUF variants). Sizes and sha256 from the signed manifest.
Hide all 17 files with their sha256
FileSizesha256
.gitattributes2.58 KB4d0b03808c3c757db0b6547864f168089d1d3e8de2d11d18b3137ea6d8fe6e90
README.md2.25 KBe1a6f558828b40632f742683283452507925ac2e5cb13269bc5436664e29bfd4
granite-guardian-4.1-8b-Q2_K.gguf3.28 GB721421b50482b3f844d6e19ed86d21125476a84a8e379c7ea8d07d84ee58a1e8
granite-guardian-4.1-8b-Q3_K_L.gguf4.52 GB3d14b784fc42261d2f738734f708ce95625488be28da6697fd92047c57118484
granite-guardian-4.1-8b-Q3_K_M.gguf4.17 GB2aa82b7d7c2ffba7d0f7f843bec6eca18756bb07c7019254a9925aa2c17ad5b1
granite-guardian-4.1-8b-Q3_K_S.gguf3.77 GB2d7321ca716bc59edc8b8224a159c81928861fee72a825b290aafdc47192eb78
granite-guardian-4.1-8b-Q4_0.gguf4.82 GB9eb58ed2189197e047a6fd2d21fcadbd9c012762653b75a3b8a6c5b7f3096798
granite-guardian-4.1-8b-Q4_1.gguf5.32 GBc76481f2ef204235a212631d8d19c4b3c25d8ecbadbc75e928f15f5b9f9569fc
granite-guardian-4.1-8b-Q4_K_M.gguf5.12 GB979114c9e6a589a1e37c2d597677555d3eb78c2856e920ed4ec97f7bded787a4
granite-guardian-4.1-8b-Q4_K_S.gguf4.86 GBf713dd826ef87bb9243b03f649051eacb31c39a6f4b4f7f4b4d3e491c3bcbadf
granite-guardian-4.1-8b-Q5_0.gguf5.82 GBefc9695e6e2671d89ab425b31af27fec6f53ad5e445d7eebecb254398c835a98
granite-guardian-4.1-8b-Q5_1.gguf6.32 GB0290ebe906fe0090edf2daab7763c8e5cffec3f9605a6643830278c6d86853f4
granite-guardian-4.1-8b-Q5_K_M.gguf5.97 GB4bb6aa91e991822559583f77d40c860027f856a7f79fe1c6c3c3c35b97c838a5
granite-guardian-4.1-8b-Q5_K_S.gguf5.82 GBc647bad1dba0249f5e031b1f6355228b5d312498e8c603c8499f398db82b4eaa
granite-guardian-4.1-8b-Q6_K.gguf6.88 GB0061355a4ef83a8f2bd1c39012b6c013c7679ab658b3845a64f39b5c52ada488
granite-guardian-4.1-8b-Q8_0.gguf8.91 GB93d078a5f8a1e678a9acd75cafdfa67d90fbf6d3c194c308c57808c8d4e2ac23
granite-guardian-4.1-8b-bf16.gguf16.8 GB2547a19610fd5c0678c10992f10ef465508ac457e8fb26537267e168f84e564b
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
bc78f09953 pinned now2026-11-15 04:54 UTC17 files · 92.3 GB

Use it

$ fw get ibm-granite/granite-guardian-4.1-8b-GGUF
# manifest sha256 140fd55fb98d… · 92.3 GB · 17 files
$ fw verify ./granite-guardian-4.1-8b-GGUF ibm-granite/granite-guardian-4.1-8b-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-4.1-8b-GGUF.json --dir ./granite-guardian-4.1-8b-GGUF $ python3 fw.py verify ./granite-guardian-4.1-8b-GGUF ./ibm-granite__granite-guardian-4.1-8b-GGUF.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ibm-granite/granite-guardian-4.1-8b-GGUF --revision bc78f0995361543a70438fe44a60bb7613fed2f0 --local-dir ./granite-guardian-4.1-8b-GGUF
llama.cppDownload one GGUF variant (granite-guardian-4.1-8b-Q2_K, 3.28 GB), then serve it.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ibm-granite/granite-guardian-4.1-8b-GGUF --include "granite-guardian-4.1-8b-Q2_K*" --local-dir ./granite-guardian-4.1-8b-GGUF $ llama-server -m ./granite-guardian-4.1-8b-GGUF/granite-guardian-4.1-8b-Q2_K.gguf
OllamaMake an Ollama model from the downloaded file.
$ printf 'FROM ./granite-guardian-4.1-8b-GGUF/granite-guardian-4.1-8b-Q2_K.gguf\n' > Modelfile $ ollama create granite-guardian-4.1-8b-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
e1a6f558828b40632f742683283452507925ac2e5cb13269bc5436664e29bfd4
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-4.1-8b-GGUFDate: 2026-11-15Commit: bc78f09Signed: 2DC28CC7B26A283B ✓
Upstream
ibm-granite/granite-guardian-4.1-8b-GGUF
Pinned commit
bc78f0995361543a70438fe44a60bb7613fed2f0
Manifest
granite-guardian-4.1-8b-GGUF.json · .minisig
Manifest sha256
140fd55fb98d6a74b6011531a107cbcb1e19a3db77c932090ab807ca2a7af38f
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 04:54 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/ibm-granite/granite-guardian-4.1-8b-GGUF.json $ curl -O https://freeweights.allternit.com/manifests/ibm-granite/granite-guardian-4.1-8b-GGUF.json.minisig $ minisign -Vm granite-guardian-4.1-8b-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-4.1-8b · 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-4.1-8b-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-4.1-8b-GGUF.json. Provenance. Takedown history: none.
Source
huggingface.co/ibm-granite/granite-guardian-4.1-8b-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