CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.granite / granite-speech-4.1-2b-GGUF
From: ibm-granite <huggingface.co/ibm-granite>Newsgroups: alt.freeweights.graniteSubject:

granite-speech-4.1-2b-GGUF

Date: 2026-11-15Commit: 8267dadSigned: 2DC28CC7B26A283B ✓

Model. Gguf weights, 10.8 GB in all. Published by ibm-granite under Apache-2.0.

granite10.8GBgranite-speech-4.1-2b-GGUFggufpermissive
FactsParamsnot statedSize10.8 GBFormatsggufTasknot taggedLicenseApache-2.0From sourcepermissive
$ fw get ibm-granite/granite-speech-4.1-2b-GGUF
# manifest sha256 4b42246d2e3c… · 10.8 GB · 8 files
$ fw verify ./granite-speech-4.1-2b-GGUF ibm-granite/granite-speech-4.1-2b-GGUF
From sourceHosted (signed)ibm-granite/granite-speech-4.1-2b-GGUFLast check: 2026-11-15 05:09 UTC
Run at homeGet help

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

Quantized of granite-speech-4.1-2b.

Works with

Run11Convert1Scan1

Convert with

ggml

Scan with

ModelScan
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
10.8 GB
Weights
1.14 GB (smallest of 5 GGUF variants)
Parameters
not stated
Formats
gguf
Task
not tagged
License
Apache-2.0 (permissive)
Files
8, 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-speech-4.1-2b

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 05:09 UTCpassed

Model card

From the publisher at commit 8267dad. Shown as plain text with links; images open at the publisher.
Granite-Speech-4.1-2B (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-speech-4.1-2b

Requirements#
  • Hugging face Transfomers v5.8.0
  • llama.cpp build: b9045

Files

8 files · 10.8 GBWeights 1.14 GB (smallest of 5 GGUF variants). Sizes and sha256 from the signed manifest.
Hide all 8 files with their sha256
FileSizesha256
.gitattributes1.85 KB0ad638e4a4a4c4e8a7f3664f006a0fc87d98f22c140b010f7c9d5317074fc8d9
README.md585 B7c013884701e707dde3cb3906033f44f1cb3ac9ebef5026d7dd0ba39847cf726
granite-speech-4.1-2b-Q4_K_M.gguf1.14 GBd18e3e79826c4f0fa6734eb05d2db3f06baccbcd5791a83653f946b3178b35d8
granite-speech-4.1-2b-Q5_K_M.gguf1.32 GB7fe37d4496611726c77cee7d7fd308285f9c69686d8bd2ca8407bd1f1b6b61d0
granite-speech-4.1-2b-Q6_K.gguf1.51 GB7ed38534867fcecf4cd52d6734690fcfeb55652018cc29097958084b2524e9c0
granite-speech-4.1-2b-Q8_0.gguf1.96 GB87320ee80cc6e638837bd2e9b7920252a87148613930bcdc11fcafad0b00beea
granite-speech-4.1-2b-bf16.gguf3.68 GBadfe250889e45445fc5147be61477a365038db447f6d281c771c16677a8be565
mmproj-model-f16.gguf1.16 GB0d3615076cbe1d35c3f60c43a60a4047b3e2eeee1b2c233580be60186faab5c5
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
8267dad2ad pinned now2026-11-15 05:09 UTC8 files · 10.8 GB

Use it

$ fw get ibm-granite/granite-speech-4.1-2b-GGUF
# manifest sha256 4b42246d2e3c… · 10.8 GB · 8 files
$ fw verify ./granite-speech-4.1-2b-GGUF ibm-granite/granite-speech-4.1-2b-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-speech-4.1-2b-GGUF.json --dir ./granite-speech-4.1-2b-GGUF $ python3 fw.py verify ./granite-speech-4.1-2b-GGUF ./ibm-granite__granite-speech-4.1-2b-GGUF.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ibm-granite/granite-speech-4.1-2b-GGUF --revision 8267dad2adc84209b0efd2702ec68a98356125eb --local-dir ./granite-speech-4.1-2b-GGUF
llama.cppDownload one GGUF variant (granite-speech-4.1-2b-Q4_K_M, 1.14 GB), then serve it.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ibm-granite/granite-speech-4.1-2b-GGUF --include "granite-speech-4.1-2b-Q4_K_M*" --local-dir ./granite-speech-4.1-2b-GGUF $ llama-server -m ./granite-speech-4.1-2b-GGUF/granite-speech-4.1-2b-Q4_K_M.gguf
OllamaMake an Ollama model from the downloaded file.
$ printf 'FROM ./granite-speech-4.1-2b-GGUF/granite-speech-4.1-2b-Q4_K_M.gguf\n' > Modelfile $ ollama create granite-speech-4.1-2b-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
7c013884701e707dde3cb3906033f44f1cb3ac9ebef5026d7dd0ba39847cf726
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-speech-4.1-2b-GGUFDate: 2026-11-15Commit: 8267dadSigned: 2DC28CC7B26A283B ✓
Upstream
ibm-granite/granite-speech-4.1-2b-GGUF
Pinned commit
8267dad2adc84209b0efd2702ec68a98356125eb
Manifest
granite-speech-4.1-2b-GGUF.json · .minisig
Manifest sha256
4b42246d2e3ca0021ceb22d11eda8b0eb519db02a607dcc396f44b930b26c494
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:09 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/ibm-granite/granite-speech-4.1-2b-GGUF.json $ curl -O https://freeweights.allternit.com/manifests/ibm-granite/granite-speech-4.1-2b-GGUF.json.minisig $ minisign -Vm granite-speech-4.1-2b-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-speech-4.1-2b · 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-speech-4.1-2b-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-speech-4.1-2b-GGUF.json. Provenance. Takedown history: none.
Source
huggingface.co/ibm-granite/granite-speech-4.1-2b-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