alt.freeweights.granite / granite-switch-4.1-8b-GGUF

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

granite-switch-4.1-8b-GGUF

Date: 2026-11-15Commit: 130829bSigned: 2DC28CC7B26A283B ✓

Model. Gguf weights, 111 GB in all. Published by ibm-granite under Apache-2.0.

granite111GBgranite-switch-4.1-8b-GGUFggufpermissive

FactsParamsnot statedSize111 GBFormatsggufTasknot taggedLicenseApache-2.0From sourcepermissive

$ fw get ibm-granite/granite-switch-4.1-8b-GGUF
# manifest sha256 70f708020f7a… · 111 GB · 34 files
$ fw verify ./granite-switch-4.1-8b-GGUF ibm-granite/granite-switch-4.1-8b-GGUF

From sourceHosted (signed)ibm-granite/granite-switch-4.1-8b-GGUFLast check: 2026-11-15 04:54 UTC

Run at home Get help

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

Quantized of granite-switch-4.1-8b.

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: 111 GB
Weights: 4.66 GB (smallest of 15 GGUF variants)
Parameters: not stated
Formats: gguf
Task: not tagged
License: Apache-2.0 (permissive)
Files: 34, 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-switch-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

Badge	Host	Last check	Result
From source	huggingface.co	2026-11-15 04:54 UTC	passed

Model card

From the publisher at commit 130829b. Shown as plain text with links; images open at the publisher.

granite-switch-4.1-8b (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-switch-4.1-8b

Build Information#

llama.cpp build tag: b11798
Transformers version: 5.20.2

Files

34 files · 111 GBWeights 4.66 GB (smallest of 15 GGUF variants). Sizes and sha256 from the signed manifest.

Show all 34 files with their sha256

File	Size	sha256
.gitattributes	2.55 KB	f7ad5b5968b0f4d5fd0f3a3ef6247ecc8c9bdedf77a28d73e6d363069c86f6e0
README.md	536 B	1720319ce47acf03516a2188921c29df1250ca05bf3ba872543cea7faa6c75b8
granite-switch-4.1-8b-Q2_K.gguf	4.66 GB	35dbaaf2fc8a5dd16abd794d93d97bddc9ba8912bd4a778fa510f75206cfd244
granite-switch-4.1-8b-Q2_K.sig	5.69 KB	a00ad8244d1009043db7d583ac8367e8dea709111781cd2ce8dc0e2d23e2ef49
granite-switch-4.1-8b-Q3_K_L.gguf	5.93 GB	2d117e4a67f7251e4876e51328aadf3f148acc348f7089b6c3d3e9adfcee976f
granite-switch-4.1-8b-Q3_K_L.sig	5.70 KB	b964b7b361a90a0852c2707eecf9480ad0f18facba0030d860ca5217a9363413
granite-switch-4.1-8b-Q3_K_M.gguf	5.47 GB	c7ac2ae9acd4957e8949a1c3eb2e7588e94faf1366f8943b575c0b023c56311e
granite-switch-4.1-8b-Q3_K_M.sig	5.70 KB	b0f7a3c7936ea5872293e76d277a5adf959f41ccbcd253bc18bc7231c0b81b93
granite-switch-4.1-8b-Q3_K_S.gguf	4.95 GB	aa91b162462232d14d12aa44cc6514e4acd69418f4bbaaf406e736a99810ed1c
granite-switch-4.1-8b-Q3_K_S.sig	5.70 KB	3a9efea165a9d73c7bdaa913faa8ead486a037bc1ba5b00a5d637b2e94336be5
granite-switch-4.1-8b-Q4_0.gguf	6.01 GB	f56d1f539361f3921b347441a2142c00fcc3b39e7274aac6de243bac102ae6f0
granite-switch-4.1-8b-Q4_0.sig	5.69 KB	3a270b68039677c8f74412cd878ad41cdd0604146e19af181ec48123f050e104
granite-switch-4.1-8b-Q4_1.gguf	6.51 GB	0b5549a4ea9e299a31db17b64ffa10ba673b737c5edcadc931bb470bbfb18b14
granite-switch-4.1-8b-Q4_1.sig	5.69 KB	e040ace29b305ad6d48e55b7ee7ba1ae323405df07befe8373815e128dd89016
granite-switch-4.1-8b-Q4_K_M.gguf	6.41 GB	899500ba75a1eaf59733d2261cc843de0878cf0eaf5faee3a7d97061e2f8107c
granite-switch-4.1-8b-Q4_K_M.sig	5.70 KB	24180e61722a49e2031aa45a71d1f50a983710a6cd98a89edfd661c6171769ff
granite-switch-4.1-8b-Q4_K_S.gguf	6.06 GB	504f3deef298939397ce721a9a9efd8cf72a34245bce19c466a6568a6358cdf3
granite-switch-4.1-8b-Q4_K_S.sig	5.70 KB	1367f9ff7168aee7fe5735b24178f07a52a2e05bba4c330a354da7d5d86ba7a9
granite-switch-4.1-8b-Q5_0.gguf	7.01 GB	c1b3175ad8e52a5c9d78399b75534a602386b347e35162e1172301bd568af5f3
granite-switch-4.1-8b-Q5_0.sig	5.69 KB	a63aa56fd399f2d0ea50cac4e7d63c11c0bf6f5df157140e6aefe4293f2ada2b
granite-switch-4.1-8b-Q5_1.gguf	7.51 GB	6563d4f7e74896cc9063d07587edc1ff91d91442575a283ca028fec32a75246d
granite-switch-4.1-8b-Q5_1.sig	5.69 KB	d26cd90fae6041c5399dee44b496006c5fc065407474de5d3b3bd9d7539b08ff
granite-switch-4.1-8b-Q5_K_M.gguf	7.21 GB	72e4f93caca7dc95c6cd90a695824cceb7d2a77b7fef14d492ca5fda60f0967f
granite-switch-4.1-8b-Q5_K_M.sig	5.70 KB	a731e900bca3fe7a0debfac81c66c2cfa9a6c2b1d9a1d4a7987820e6ac69ddc0
granite-switch-4.1-8b-Q5_K_S.gguf	7.01 GB	5aff81e612ed8c457112e93f52ac9946b1d7a7c691fa0e9d651ad9a366e95165
granite-switch-4.1-8b-Q5_K_S.sig	5.70 KB	fa1be66609e11db21d16f9d96bdd3c97e82d354fc4b6518ddb66c72f574e898a
granite-switch-4.1-8b-Q6_K.gguf	8.07 GB	c1256d69390c08c8a19f8453de002691797f2157bc2f0b7fac59f3d5d0820f7b
granite-switch-4.1-8b-Q6_K.sig	5.69 KB	cba4c239502dba2b49dce9d07123b1c725da1d5e27cbee62bba7cc0cbfa0e132
granite-switch-4.1-8b-Q8_0.gguf	10.1 GB	87551e7ef3f944800db462d7cad764c363b0e8d8aee3a4a0305a5dfe0c7fb83d
granite-switch-4.1-8b-Q8_0.sig	5.69 KB	353d1506b8c1d2f3fa3eb726ed631af51541f76819c8fa4d1ad84b71cbbe5a60
granite-switch-4.1-8b-bf16-metadata.properties	502 B	657cb32ff7777f4cb8ff004854816e5718e090f1dab2ebdbb3248e1993f136a3
granite-switch-4.1-8b-bf16.gguf	18.0 GB	8e337ffa91cc80a592d917ecacee58d0b1007ad89f5addf0369b2f637fd795fe
granite-switch-4.1-8b-bf16.sig	5.69 KB	d3482c2e3bd84f0c79976c5b5599a92191c290ff95353ef550ec03039870a934
model.sig	9.63 KB	968f5b6b217cec1c5710777e742defa34c46ceee3a131373a24cdd03cf842553

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

Upstream commit	Date	Contents
130829b9f3 pinned now	2026-11-15 04:54 UTC	34 files · 111 GB

Use it

$ fw get ibm-granite/granite-switch-4.1-8b-GGUF
# manifest sha256 70f708020f7a… · 111 GB · 34 files
$ fw verify ./granite-switch-4.1-8b-GGUF ibm-granite/granite-switch-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-switch-4.1-8b-GGUF.json --dir ./granite-switch-4.1-8b-GGUF
$ python3 fw.py verify ./granite-switch-4.1-8b-GGUF ./ibm-granite__granite-switch-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-switch-4.1-8b-GGUF --revision 130829b9f34ea491d33c58e436479c27175a2c82 --local-dir ./granite-switch-4.1-8b-GGUF

llama.cppDownload one GGUF variant (granite-switch-4.1-8b-Q2_K, 4.66 GB), then serve it.

$ HF_ENDPOINT=https://freeweights.allternit.com hf download ibm-granite/granite-switch-4.1-8b-GGUF --include "granite-switch-4.1-8b-Q2_K*" --local-dir ./granite-switch-4.1-8b-GGUF
$ llama-server -m ./granite-switch-4.1-8b-GGUF/granite-switch-4.1-8b-Q2_K.gguf

OllamaMake an Ollama model from the downloaded file.

$ printf 'FROM ./granite-switch-4.1-8b-GGUF/granite-switch-4.1-8b-Q2_K.gguf\n' > Modelfile
$ ollama create granite-switch-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: 1720319ce47acf03516a2188921c29df1250ca05bf3ba872543cea7faa6c75b8
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-switch-4.1-8b-GGUFDate: 2026-11-15Commit: 130829bSigned: 2DC28CC7B26A283B ✓

Upstream: ibm-granite/granite-switch-4.1-8b-GGUF
Pinned commit: 130829b9f34ea491d33c58e436479c27175a2c82
Manifest: granite-switch-4.1-8b-GGUF.json · .minisig
Manifest sha256: 70f708020f7abd1d5065450cc0bd95222633a66403f6af5a420a4afa33665477
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-switch-4.1-8b-GGUF.json
$ curl -O https://freeweights.allternit.com/manifests/ibm-granite/granite-switch-4.1-8b-GGUF.json.minisig
$ minisign -Vm granite-switch-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-switch-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-switch-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-switch-4.1-8b-GGUF.json. Provenance. Takedown history: none.

Source

huggingface.co/ibm-granite/granite-switch-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