alt.freeweights.granite / granite-4.0-1b-GGUF

From: ibm-granite <huggingface.co/ibm-granite>Newsgroups: alt.freeweights.graniteSubject:

granite-4.0-1b-GGUF

Date: 2026-11-15Commit: b27c2feSigned: 2DC28CC7B26A283B ✓

Model. Gguf weights, 18.4 GB in all. Published by ibm-granite under Apache-2.0.

granite18.4GBgranite-4.0-1b-GGUFggufpermissive

FactsParamsnot statedSize18.4 GBFormatsggufTasknot taggedLicenseApache-2.0From sourcepermissive

$ fw get ibm-granite/granite-4.0-1b-GGUF
# manifest sha256 f00446879900… · 18.4 GB · 17 files
$ fw verify ./granite-4.0-1b-GGUF ibm-granite/granite-4.0-1b-GGUF

From sourceHosted (signed)ibm-granite/granite-4.0-1b-GGUFLast check: 2026-11-15 04:50 UTC

Run at home Get help

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

Quantized of granite-4.0-1b.

Works with

Run11 Convert1 Scan1

Runs with

Ranked by fit to this model (gguf), then by GitHub stars.

Ollama

llama.cpp LocalAI

BitNet llamafile KoboldCpp PocketPal AI llama-swap ik_llama.cpp RamaLama Maid

Convert with

ggml

Scan with

ModelScan

Overview Model card Files Use it License Provenance Model tree

Overview

Size: 18.4 GB
Weights: 702 MB (smallest of 15 GGUF variants)
Parameters: not stated
Formats: gguf
Task: not tagged
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-4.0-1b

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

Badge	Host	Last check	Result
From source	huggingface.co	2026-11-15 04:50 UTC	passed

Model card

From the publisher at commit b27c2fe. Shown as plain text with links; images open at the publisher.

Granite 4.0 1b (GGUF)#

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-4.0-1b

Known Issues#

This model often uses the full numerical range of a 32-bit float (f32), so variants with smaller numerical ranges may run into precision errors at inference. The F16 variant is known to fail on many hardware combinations.

The recommended full-precision variant is bf16.

Files

17 files · 18.4 GBWeights 702 MB (smallest of 15 GGUF variants). Sizes and sha256 from the signed manifest.

Hide all 17 files with their sha256

File	Size	sha256
.gitattributes	2.51 KB	01a7f932101864f5dcc993087ef7b5ae5ce12a5fcbcfaaa35206830c476c33b2
README.md	720 B	6eb8313f139c370194b2115651246e3c598cb728cc055c8d3ce6a13d03cb8926
granite-4.0-1b-Q2_K.gguf	702 MB	e923b8bd5b6e41d1fdfa7f7a2f323cec5d7dbace1cd3ce865f863ebef9bebfb8
granite-4.0-1b-Q3_K_L.gguf	926 MB	b095a2c8cff29871cc778d1a32521a22855feadf57cbfc042323907d635fd5c3
granite-4.0-1b-Q3_K_M.gguf	860 MB	3ae1131da76c41ea92b06ff6832bfbe59b3bbae2f884082f8eaeda69dcd9cdce
granite-4.0-1b-Q3_K_S.gguf	786 MB	1dc4514416725646ecdd4668759937981a34407f422533cf330fba6709320182
granite-4.0-1b-Q4_0.gguf	975 MB	227e78e2fb9a3e5699190be0ce0885fd2ea72a242ed1bf718c2148c45dd090b5
granite-4.0-1b-Q4_1.gguf	1.06 GB	5e549e2d7ba3f7eeed0025a5dfd01c8a31c445b5ad9f1336f9aa439d2cab979c
granite-4.0-1b-Q4_K_M.gguf	1.02 GB	22ec0f9cc99a90185312de3c882c84e7bd6789bdd050389844380a01a831d7f1
granite-4.0-1b-Q4_K_S.gguf	981 MB	122f56c148f7da5eeb482a9c70f02d8c8d589cedeb54217d45f0513bbb220f63
granite-4.0-1b-Q5_0.gguf	1.15 GB	0da33ca347635e5273f156e0813031f7fcd4e5135e4f98e8e617987f24ed0735
granite-4.0-1b-Q5_1.gguf	1.24 GB	87852bd1f330bb6d86e80acfd0846e53a9392564d4e6ad81765dec635180500d
granite-4.0-1b-Q5_K_M.gguf	1.18 GB	3d977db90ec00a2152cc3cdb788f7273c6258f49394a914046cc90c266831598
granite-4.0-1b-Q5_K_S.gguf	1.15 GB	eb88ddace0f5a60254ce3be033db7922fbb85324a119bbd8500df3339e1341de
granite-4.0-1b-Q6_K.gguf	1.34 GB	c6799eecde3b056e57c756c84cfb6535f6cbaaebcb0dfca197d564b1d2f28455
granite-4.0-1b-Q8_0.gguf	1.74 GB	0660c20c3d3d3672b90f0468f62dc128a82a6e3ee2ec05d310d242969be06140
granite-4.0-1b-bf16.gguf	3.27 GB	551fc8b33f100c13d056e114b4e352bd4f2763240b68283076110203da8f5843

VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.

Upstream commit	Date	Contents
b27c2fe3f2 pinned now	2026-11-15 04:50 UTC	17 files · 18.4 GB

Use it

$ fw get ibm-granite/granite-4.0-1b-GGUF
# manifest sha256 f00446879900… · 18.4 GB · 17 files
$ fw verify ./granite-4.0-1b-GGUF ibm-granite/granite-4.0-1b-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-4.0-1b-GGUF.json --dir ./granite-4.0-1b-GGUF
$ python3 fw.py verify ./granite-4.0-1b-GGUF ./ibm-granite__granite-4.0-1b-GGUF.json

hfThe Hugging Face CLI with one setting. Same repo id.

$ HF_ENDPOINT=https://freeweights.allternit.com hf download ibm-granite/granite-4.0-1b-GGUF --revision b27c2fe3f211b7f44e80fa620177aea371099aaa --local-dir ./granite-4.0-1b-GGUF

llama.cppDownload one GGUF variant (granite-4.0-1b-Q2_K, 702 MB), then serve it.

$ HF_ENDPOINT=https://freeweights.allternit.com hf download ibm-granite/granite-4.0-1b-GGUF --include "granite-4.0-1b-Q2_K*" --local-dir ./granite-4.0-1b-GGUF
$ llama-server -m ./granite-4.0-1b-GGUF/granite-4.0-1b-Q2_K.gguf

OllamaMake an Ollama model from the downloaded file.

$ printf 'FROM ./granite-4.0-1b-GGUF/granite-4.0-1b-Q2_K.gguf\n' > Modelfile
$ ollama create granite-4.0-1b-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: 6eb8313f139c370194b2115651246e3c598cb728cc055c8d3ce6a13d03cb8926
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-4.0-1b-GGUFDate: 2026-11-15Commit: b27c2feSigned: 2DC28CC7B26A283B ✓

Upstream: ibm-granite/granite-4.0-1b-GGUF
Pinned commit: b27c2fe3f211b7f44e80fa620177aea371099aaa
Manifest: granite-4.0-1b-GGUF.json · .minisig
Manifest sha256: f0044687990097bd5b0c8eb3781fcf22355862fa623e7ede5e29da72c2f7f320
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-15 04:50 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/ibm-granite/granite-4.0-1b-GGUF.json
$ curl -O https://freeweights.allternit.com/manifests/ibm-granite/granite-4.0-1b-GGUF.json.minisig
$ minisign -Vm granite-4.0-1b-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-4.0-1b · 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-4.0-1b-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-4.0-1b-GGUF.json. Provenance. Takedown history: none.

Source

huggingface.co/ibm-granite/granite-4.0-1b-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