alt.freeweights.granite / granite-4.0-h-tiny-base-GGUF

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

granite-4.0-h-tiny-base-GGUF

Date: 2026-11-15Commit: 27f7505Signed: 2DC28CC7B26A283B ✓

Model. Gguf weights, 76.0 GB in all. Published by ibm-granite under Apache-2.0.

granite76.0GBgranite-4.0-h-tiny-base-GGUFggufpermissive

FactsParamsnot statedSize76.0 GBFormatsggufTasknot taggedLicenseApache-2.0From sourcepermissive

$ fw get ibm-granite/granite-4.0-h-tiny-base-GGUF
# manifest sha256 10c2d095c7cc… · 76.0 GB · 17 files
$ fw verify ./granite-4.0-h-tiny-base-GGUF ibm-granite/granite-4.0-h-tiny-base-GGUF

From sourceHosted (signed)ibm-granite/granite-4.0-h-tiny-base-GGUFLast check: 2026-11-15 05:05 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-h-tiny-base.

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: 76.0 GB
Weights: 2.59 GB (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-h-tiny-base

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 05:05 UTC	passed

Model card

From the publisher at commit 27f7505. Shown as plain text with links; images open at the publisher.

Granite 4.0 H-Tiny Base (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-h-tiny-base

Files

17 files · 76.0 GBWeights 2.59 GB (smallest of 15 GGUF variants). Sizes and sha256 from the signed manifest.

Hide all 17 files with their sha256

File	Size	sha256
.gitattributes	2.65 KB	2ad7afc5cbe55e2a706cd1f394a491248357880935a5916dc0710662a780f4c8
README.md	448 B	7ef2bdc092eefd7a9171189689db665549456dfe33dd0ce300ddfae678c6d7bd
granite-4.0-h-tiny-base-Q2_K.gguf	2.59 GB	08315f0b1dedbd12e987d88d6474e483faf22e38e901ac1e2c591deb6a7310c7
granite-4.0-h-tiny-base-Q3_K_L.gguf	3.60 GB	da52a5eae23cd622d6d90c67cc2943bfd0b1dd03a23897b7b2cf106de940890e
granite-4.0-h-tiny-base-Q3_K_M.gguf	3.35 GB	1cc624fc86af461b4b26cb5ebfd05b2ae8a966285f8aad8e831c199148ead5ce
granite-4.0-h-tiny-base-Q3_K_S.gguf	3.06 GB	643e40b6b3d43848510e8fdd2cb228b461efca2e739881e0b8562ff409cc4052
granite-4.0-h-tiny-base-Q4_0.gguf	3.96 GB	e834499af1bfa8dbefa60fd93170905affe548a8235d6f0867ca12fc9fcc8432
granite-4.0-h-tiny-base-Q4_1.gguf	4.39 GB	05b99024298874d7dfb645a395f14b0d38234fc9d8766230564c7db22f62852e
granite-4.0-h-tiny-base-Q4_K_M.gguf	4.23 GB	7aff4ea112f1310a654ff39f2df3bc7191afee59b8f258822557de59720f5ac0
granite-4.0-h-tiny-base-Q4_K_S.gguf	4.00 GB	2a5debf190fea0785ae1b4e06f0ea5135efb141d2b5a1a7111b237e17c3c0e60
granite-4.0-h-tiny-base-Q5_0.gguf	4.81 GB	e223201d1f9b14da55185abebb894a8e421ebf9199ebd4fca78653ef016b8f3f
granite-4.0-h-tiny-base-Q5_1.gguf	5.23 GB	0813c9d872425c1f8b8cd98ca648b82a14f416fb2a7289867c54829cb4213cb5
granite-4.0-h-tiny-base-Q5_K_M.gguf	4.95 GB	a04eebed43c125861419c0f3a251bf25faf86915ab17f105b5f5201b091b9f6d
granite-4.0-h-tiny-base-Q5_K_S.gguf	4.81 GB	9cc7fc0696556d685533cc716fd7cbfbe81917b544212a229ffb25a51da95b3c
granite-4.0-h-tiny-base-Q6_K.gguf	5.71 GB	c97dc8ca9ea336bc6ae12e3825269938484e0daf4e923347edd7ef0fa4c6e4e7
granite-4.0-h-tiny-base-Q8_0.gguf	7.39 GB	6d1463fb5e11ec6b7d699d41aa8530d5393b996f1e1f8c7c32f7a31c1cb87b90
granite-4.0-h-tiny-base-bf16.gguf	13.9 GB	66f37d9533b48701c8a2f0ce456623ff64c1a29db9daf3fc877a3d3c3c137bbc

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

Upstream commit	Date	Contents
27f75056a8 pinned now	2026-11-15 05:05 UTC	17 files · 76.0 GB

Use it

$ fw get ibm-granite/granite-4.0-h-tiny-base-GGUF
# manifest sha256 10c2d095c7cc… · 76.0 GB · 17 files
$ fw verify ./granite-4.0-h-tiny-base-GGUF ibm-granite/granite-4.0-h-tiny-base-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-h-tiny-base-GGUF.json --dir ./granite-4.0-h-tiny-base-GGUF
$ python3 fw.py verify ./granite-4.0-h-tiny-base-GGUF ./ibm-granite__granite-4.0-h-tiny-base-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-h-tiny-base-GGUF --revision 27f75056a8aabab6377df1d9dd4f37c9b1fbe14e --local-dir ./granite-4.0-h-tiny-base-GGUF

llama.cppDownload one GGUF variant (granite-4.0-h-tiny-base-Q2_K, 2.59 GB), then serve it.

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

OllamaMake an Ollama model from the downloaded file.

$ printf 'FROM ./granite-4.0-h-tiny-base-GGUF/granite-4.0-h-tiny-base-Q2_K.gguf\n' > Modelfile
$ ollama create granite-4.0-h-tiny-base-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: 7ef2bdc092eefd7a9171189689db665549456dfe33dd0ce300ddfae678c6d7bd
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-h-tiny-base-GGUFDate: 2026-11-15Commit: 27f7505Signed: 2DC28CC7B26A283B ✓

Upstream: ibm-granite/granite-4.0-h-tiny-base-GGUF
Pinned commit: 27f75056a8aabab6377df1d9dd4f37c9b1fbe14e
Manifest: granite-4.0-h-tiny-base-GGUF.json · .minisig
Manifest sha256: 10c2d095c7ccf7d668dd9d6f0d994223dbc9e96db2cb96b9927bf4bffab5a5dc
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-15 05:05 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

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

Source

huggingface.co/ibm-granite/granite-4.0-h-tiny-base-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