alt.freeweights.granite / granite-3.3-2b-instruct-GGUF

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

granite-3.3-2b-instruct-GGUF

Date: 2026-11-15Commit: 7cdf86cSigned: 2DC28CC7B26A283B ✓

Text generation model. Gguf weights, 27.9 GB in all. Published by ibm-granite under Apache-2.0.

granite27.9GBgranite-3.3-2b-instruct-GGUFggufpermissive

FactsParamsnot statedSize27.9 GBFormatsggufTasktext generationLicenseApache-2.0From sourcepermissive

$ fw get ibm-granite/granite-3.3-2b-instruct-GGUF
# manifest sha256 7f1bb98675ca… · 27.9 GB · 17 files
$ fw verify ./granite-3.3-2b-instruct-GGUF ibm-granite/granite-3.3-2b-instruct-GGUF

From sourceHosted (signed)ibm-granite/granite-3.3-2b-instruct-GGUFLast check: 2026-11-15 04:49 UTC

Run at home Get help

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

Quantized of granite-3.3-2b-instruct.

Works with

Run14 Convert1 Evaluate13 Scan12 Apps58

Runs with

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

Text Generation WebUI mistral.rs

Ollama

llama.cpp LocalAI

BitNet llamafile gpu-unlock KoboldCpp PocketPal AI llama-swap ik_llama.cpp

Show all 14

RamaLama Maid

Convert with

ggml

Evaluate with

Opik DeepEval Ragas lm-evaluation-harness OpenCompass SWE-bench

simple-evals TruLens HELM

LightEval

Evaluate Weave

Show all 13

Autoevals

Scan with

promptfoo garak Guardrails NeMo Guardrails Giskard DeepTeam AI Fairness 360 Fairlearn Detoxify MCP Scanner AgentDojo ModelScan

Overview Model card Files Use it License Provenance Model tree

Overview

Size: 27.9 GB
Weights: 978 MB (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-3.3-2b-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

Badge	Host	Last check	Result
From source	huggingface.co	2026-11-15 04:49 UTC	passed

Model card

From the publisher at commit 7cdf86c. 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-3.3-2b-instruct

Files

17 files · 27.9 GBWeights 978 MB (smallest of 15 GGUF variants). Sizes and sha256 from the signed manifest.

Hide all 17 files with their sha256

File	Size	sha256
.gitattributes	2.58 KB	6c3dcf32b4837ee91fd93cdbefebee35fe3fff0a205d7ce14ee4f64dbcc43b03
README.md	460 B	2d066c2b00f3dedbd6765139c9d8556eae58a031df1d05fbfbe625eba81a99a3
granite-3.3-2b-instruct-Q2_K.gguf	978 MB	8be25be65b4a2955781fd93df51f4752e6f6fe5c035bea5573b97538736dfedd
granite-3.3-2b-instruct-Q3_K_L.gguf	1.36 GB	e21f3cfe8c3ee1ef7b2d5e62057e299f28fbc49e8bb719038d27fa25508a7b1d
granite-3.3-2b-instruct-Q3_K_M.gguf	1.25 GB	a8708c802dde0922c1b6ab94eb4aac8e67d0c525c9ddc664e2c2d91202da9e50
granite-3.3-2b-instruct-Q3_K_S.gguf	1.13 GB	ca71c0faaea5647c6f34bb55d8ae9516e94828e0065cdbbf4680348be2bbbfd3
granite-3.3-2b-instruct-Q4_0.gguf	1.45 GB	d5da3f5bb5a6ae442f830bdde0df4fcccb7e8bd395dc9ee5d28e704db4065592
granite-3.3-2b-instruct-Q4_1.gguf	1.61 GB	0d999d28737c8dabaaa9c4e67e19820e03140de1629cd33fbc3a4c272ce4589e
granite-3.3-2b-instruct-Q4_K_M.gguf	1.55 GB	ac71e9e32c0bea919b409c5918f69ca74339854b0319c5065e4e9fb6d95c4852
granite-3.3-2b-instruct-Q4_K_S.gguf	1.46 GB	99f7327dd6b434064ddfc7f05f2e83a003201fd78b80b69c8b62b0717786ec60
granite-3.3-2b-instruct-Q5_0.gguf	1.76 GB	4681d622e263a919dc146dd7b438d43ff310036544d1c7fe8de6c8183dbccff4
granite-3.3-2b-instruct-Q5_1.gguf	1.91 GB	4fff76c13322c053eccd00c1e5e968f991ca42aa021633590ef84282ff120ff9
granite-3.3-2b-instruct-Q5_K_M.gguf	1.80 GB	ab6a8112af16362677e5b2b359a68621878e1f8ea7a22c59ba6e82fd4dd414e3
granite-3.3-2b-instruct-Q5_K_S.gguf	1.76 GB	68321f4d78a1d15bdef42b6923df43494d8c84ece80bb79ac16eeb77d3b8b43e
granite-3.3-2b-instruct-Q6_K.gguf	2.08 GB	a59ba995c354617ff51bb69ee095d9614e57c7f6c137536154f71c4fddb506cb
granite-3.3-2b-instruct-Q8_0.gguf	2.69 GB	39068a5bcb15f10487a49426d617b1b0f38a624d7dbdefe5ff6f26de82d97039
granite-3.3-2b-instruct-f16.gguf	5.07 GB	79b52937a0c2f5a984ac6d3794ddf02ceb62cf53bc982c26cac97929513c0a9e

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

Upstream commit	Date	Contents
7cdf86ccd1 pinned now	2026-11-15 04:49 UTC	17 files · 27.9 GB

Use it

$ fw get ibm-granite/granite-3.3-2b-instruct-GGUF
# manifest sha256 7f1bb98675ca… · 27.9 GB · 17 files
$ fw verify ./granite-3.3-2b-instruct-GGUF ibm-granite/granite-3.3-2b-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-3.3-2b-instruct-GGUF.json --dir ./granite-3.3-2b-instruct-GGUF
$ python3 fw.py verify ./granite-3.3-2b-instruct-GGUF ./ibm-granite__granite-3.3-2b-instruct-GGUF.json

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

$ HF_ENDPOINT=https://freeweights.allternit.com hf download ibm-granite/granite-3.3-2b-instruct-GGUF --revision 7cdf86ccd1f1bb3491c9b7017b033f2e51367397 --local-dir ./granite-3.3-2b-instruct-GGUF

llama.cppDownload one GGUF variant (granite-3.3-2b-instruct-Q2_K, 978 MB), then serve it.

$ HF_ENDPOINT=https://freeweights.allternit.com hf download ibm-granite/granite-3.3-2b-instruct-GGUF --include "granite-3.3-2b-instruct-Q2_K*" --local-dir ./granite-3.3-2b-instruct-GGUF
$ llama-server -m ./granite-3.3-2b-instruct-GGUF/granite-3.3-2b-instruct-Q2_K.gguf

OllamaMake an Ollama model from the downloaded file.

$ printf 'FROM ./granite-3.3-2b-instruct-GGUF/granite-3.3-2b-instruct-Q2_K.gguf\n' > Modelfile
$ ollama create granite-3.3-2b-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: 2d066c2b00f3dedbd6765139c9d8556eae58a031df1d05fbfbe625eba81a99a3
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-3.3-2b-instruct-GGUFDate: 2026-11-15Commit: 7cdf86cSigned: 2DC28CC7B26A283B ✓

Upstream: ibm-granite/granite-3.3-2b-instruct-GGUF
Pinned commit: 7cdf86ccd1f1bb3491c9b7017b033f2e51367397
Manifest: granite-3.3-2b-instruct-GGUF.json · .minisig
Manifest sha256: 7f1bb98675ca973db44714d89a54c978717f16284bac86eb1e5e189feb733885
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-15 04:49 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/ibm-granite/granite-3.3-2b-instruct-GGUF.json
$ curl -O https://freeweights.allternit.com/manifests/ibm-granite/granite-3.3-2b-instruct-GGUF.json.minisig
$ minisign -Vm granite-3.3-2b-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-3.3-2b-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-3.3-2b-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-3.3-2b-instruct-GGUF.json. Provenance. Takedown history: none.

Source

huggingface.co/ibm-granite/granite-3.3-2b-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