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

granite-3.3-8b-instruct-GGUF

Date: 2026-11-15Commit: e40e9ddSigned: 2DC28CC7B26A283B ✓

Text generation model. Gguf weights, 89.4 GB in all. Published by ibm-granite under Apache-2.0.

granite89.4GBgranite-3.3-8b-instruct-GGUFggufpermissive
FactsParamsnot statedSize89.4 GBFormatsggufTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get ibm-granite/granite-3.3-8b-instruct-GGUF
# manifest sha256 b68179238d5d… · 89.4 GB · 17 files
$ fw verify ./granite-3.3-8b-instruct-GGUF ibm-granite/granite-3.3-8b-instruct-GGUF
From sourceHosted (signed)ibm-granite/granite-3.3-8b-instruct-GGUFLast check: 2026-11-15 04:46 UTC
Run at homeGet help

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

Quantized of granite-3.3-8b-instruct.

Works with

Run14Convert1Evaluate13Scan12Apps58

Convert with

ggml
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
89.4 GB
Weights
3.10 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-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 04:46 UTCpassed

Model card

From the publisher at commit e40e9dd. 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-3.3-8b-instruct

Files

17 files · 89.4 GBWeights 3.10 GB (smallest of 15 GGUF variants). Sizes and sha256 from the signed manifest.
Hide all 17 files with their sha256
FileSizesha256
.gitattributes2.58 KB83cc75d34e236a6e24dd1d58243fec6aaaaa1b62fc4ebe0a037440124874cdf3
README.md460 B3caa21957f57266158c22853e09c7d7d066cfcc9d003e31c8daacf930f9aabb9
granite-3.3-8b-instruct-Q2_K.gguf3.10 GBa1b98f1babe447db263acb075a1c365b75ba196adbf833a214360ec4aa419dab
granite-3.3-8b-instruct-Q3_K_L.gguf4.35 GBadca23cb4aca9548c8359daf888b24bdf57775ffd12f8c1432c8e46e7b7d1b52
granite-3.3-8b-instruct-Q3_K_M.gguf4.00 GB11d27d6679e85f15eeff7e08f74dd0f5f0192dd358703db99fb5d576ff2a7651
granite-3.3-8b-instruct-Q3_K_S.gguf3.59 GB824abd810da9124ae04c38596f6c06b29efb402bfd56a812cd5c201844a33c7d
granite-3.3-8b-instruct-Q4_0.gguf4.65 GB08c17cb11b7eaf739d169ea9566d74ea35415d7a8f7297521a27adb78f898706
granite-3.3-8b-instruct-Q4_1.gguf5.15 GB0be9efcaaed673333a220f1ac675960e1f39b88c1a240b3a8dc0cc1194f51f7f
granite-3.3-8b-instruct-Q4_K_M.gguf4.94 GB77bcee066a76dcdd10d0d123c87e32c8ec2c74e31b6ffd87ebee49c9ac215dca
granite-3.3-8b-instruct-Q4_K_S.gguf4.69 GB4e62275209f83108bfcce59271f867cd5ebf1141b1e4aa9564b33f2c02ce753e
granite-3.3-8b-instruct-Q5_0.gguf5.65 GBc528f0897abc0b7d0d79bbb7d3d5d62b7a24023207dbf5eefd48bbb7ab1efbe9
granite-3.3-8b-instruct-Q5_1.gguf6.15 GB3f89d18eea51a7880c9ccec63695db8ac43ee86142a84da4234f398901c35d97
granite-3.3-8b-instruct-Q5_K_M.gguf5.80 GB222bd5b4163cc3c9fbf534d47efb63957abf8abb6a23733915b56ee3c2d16218
granite-3.3-8b-instruct-Q5_K_S.gguf5.65 GBacb4cee7642aff1775775b37db2df0eac615c62ad1857e38d38be85a2ccf4cee
granite-3.3-8b-instruct-Q6_K.gguf6.71 GBb0fe6e279cf247a8119ca744286f53ce22890d871e26c3af38e12f5f9008b2bb
granite-3.3-8b-instruct-Q8_0.gguf8.68 GB8ced2b014c6b5d4b1be698fd2cb5b051b08ce0b439d2584eb358e0d3f0a00611
granite-3.3-8b-instruct-f16.gguf16.3 GBde786b20fbab19ed5a5cc6ce902550b4548ded5c07be3e991815cdd6caf18c40
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
e40e9dd739 pinned now2026-11-15 04:46 UTC17 files · 89.4 GB

Use it

$ fw get ibm-granite/granite-3.3-8b-instruct-GGUF
# manifest sha256 b68179238d5d… · 89.4 GB · 17 files
$ fw verify ./granite-3.3-8b-instruct-GGUF ibm-granite/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/ibm-granite/granite-3.3-8b-instruct-GGUF.json --dir ./granite-3.3-8b-instruct-GGUF $ python3 fw.py verify ./granite-3.3-8b-instruct-GGUF ./ibm-granite__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 ibm-granite/granite-3.3-8b-instruct-GGUF --revision e40e9dd739c7be00fa965c16ce167088190ce114 --local-dir ./granite-3.3-8b-instruct-GGUF
llama.cppDownload one GGUF variant (granite-3.3-8b-instruct-Q2_K, 3.10 GB), then serve it.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ibm-granite/granite-3.3-8b-instruct-GGUF --include "granite-3.3-8b-instruct-Q2_K*" --local-dir ./granite-3.3-8b-instruct-GGUF $ llama-server -m ./granite-3.3-8b-instruct-GGUF/granite-3.3-8b-instruct-Q2_K.gguf
OllamaMake an Ollama model from the downloaded file.
$ printf 'FROM ./granite-3.3-8b-instruct-GGUF/granite-3.3-8b-instruct-Q2_K.gguf\n' > Modelfile $ ollama create granite-3.3-8b-instruct-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
3caa21957f57266158c22853e09c7d7d066cfcc9d003e31c8daacf930f9aabb9
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-instruct-GGUFDate: 2026-11-15Commit: e40e9ddSigned: 2DC28CC7B26A283B ✓
Upstream
ibm-granite/granite-3.3-8b-instruct-GGUF
Pinned commit
e40e9dd739c7be00fa965c16ce167088190ce114
Manifest
granite-3.3-8b-instruct-GGUF.json · .minisig
Manifest sha256
b68179238d5dfa38f10f8112cdee10b0027f4bbd9770efdb449b76e0bbd33baa
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 04:46 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-GGUF.json $ curl -O https://freeweights.allternit.com/manifests/ibm-granite/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 ibm-granite/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.
Source
huggingface.co/ibm-granite/granite-3.3-8b-instruct-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