CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.granite / granite-4.1-30b-4bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.graniteSubject:

granite-4.1-30b-4bit

Date: 2026-11-15Commit: 03e8065Signed: 2DC28CC7B26A283B ✓

Text generation model with 28.9B parameters. Safetensors weights, 18.0 GB in all. Published by mlx-community under Apache-2.0.

28.9B params18.0GBgranite-4.1-30b-4bitsafetensorspermissive
FactsParams28.9BSize18.0 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/granite-4.1-30b-4bit
# manifest sha256 dbba4942bafd… · 18.0 GB · 12 files
$ fw verify ./granite-4.1-30b-4bit mlx-community/granite-4.1-30b-4bit
From sourceHosted (signed)mlx-community/granite-4.1-30b-4bitLast check: 2026-11-15 05:14 UTC
Run at homeGet help

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

Quantized of granite-4.1-30b.

Works with

Run24Fine-tune29Convert15Evaluate13Scan13Apps58
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
18.0 GB
Weights
18.0 GB (safetensors)
Parameters
28.9B
Formats
safetensors
Task
text generation
License
Apache-2.0 (permissive)
Files
12, each with a sha256
Publisher
mlx-community
Added
2026-11-15
Section
alt.freeweights.granite
Lineage

Original release from the publisher.

Base model: ibm-granite/granite-4.1-30b

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 05:14 UTCpassed

Model card

From the publisher at commit 03e8065. Shown as plain text with links; images open at the publisher.

mlx-community/granite-4.1-30b-4bit#

This model mlx-community/granite-4.1-30b-4bit was converted to MLX format from ibm-granite/granite-4.1-30b using mlx-lm version 0.31.3.

Use with mlx#

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/granite-4.1-30b-4bit")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True, return_dict=False,
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)

Files

12 files · 18.0 GBWeights 18.0 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 12 files with their sha256
FileSizesha256
.gitattributes1.52 KB11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
README.md903 B49b3f104a4dba51d1775f084677b33abfb5a257cd9517bc8be36d1873a61ece3
chat_template.jinja6.10 KBfed2756d2d24e127b951dcf139d0b03ab7db8ef23a456128ebc9c2db4901d476
config.json1.10 KBbc53d588c301dbb5f2a2115ff223e0eb25e08e28fe34f1f6cad02452b8ace745
generation_config.json147 B9117fb03fed79dbb459373edeef9a3eec966bce52a1842e03a6716e83117f0d1
model-00001-of-00004.safetensors5.36 GB4641a3af6957f6433be7e3a8f29540accad3f7b9d8d8b35c7289d56243deae90
model-00002-of-00004.safetensors5.36 GBe468eebe28cd470f44413d538d4edeaa13f2a2ed30df560cd0c642afff79e6c4
model-00003-of-00004.safetensors5.36 GBc329ba648d5014ea90b7ce1653dbdbfd2e2dea804de8ff6e2cee46a368014c5c
model-00004-of-00004.safetensors1.95 GB5f0cd375203a60387f49b0e5c9e6dc7b03757eff2b0e00436db00cc6240d302b
model.safetensors.index.json127 KB2e4ec8f8b0a3111bf5f1786784f1ad6a18eff2e9c83db2587c96e86b29795b8d
tokenizer.json7.15 MB24665f2815ee47aba521e4710bfc52f8ca045a552ec3f60925cce5e0edecb657
tokenizer_config.json418 Bfb2f8b5d9980cc7c2e4aa3361b34d3f43c6ff94f675276ac2e32fb2e9b751594
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
03e8065d32 pinned now2026-11-15 05:14 UTC12 files · 18.0 GB

Use it

$ fw get mlx-community/granite-4.1-30b-4bit
# manifest sha256 dbba4942bafd… · 18.0 GB · 12 files
$ fw verify ./granite-4.1-30b-4bit mlx-community/granite-4.1-30b-4bit
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/granite-4.1-30b-4bit.json --dir ./granite-4.1-30b-4bit $ python3 fw.py verify ./granite-4.1-30b-4bit ./mlx-community__granite-4.1-30b-4bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/granite-4.1-30b-4bit --revision 03e8065d3219e525aa27fc4aaa9b375fe2cd6cb8 --local-dir ./granite-4.1-30b-4bit
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForCausalLM, AutoTokenizer tok = AutoTokenizer.from_pretrained("mlx-community/granite-4.1-30b-4bit", revision="03e8065d3219e525aa27fc4aaa9b375fe2cd6cb8") model = AutoModelForCausalLM.from_pretrained("mlx-community/granite-4.1-30b-4bit", revision="03e8065d3219e525aa27fc4aaa9b375fe2cd6cb8", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/granite-4.1-30b-4bit --revision 03e8065d3219e525aa27fc4aaa9b375fe2cd6cb8
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
49b3f104a4dba51d1775f084677b33abfb5a257cd9517bc8be36d1873a61ece3
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: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.graniteSubject: granite-4.1-30b-4bitDate: 2026-11-15Commit: 03e8065Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/granite-4.1-30b-4bit
Pinned commit
03e8065d3219e525aa27fc4aaa9b375fe2cd6cb8
Manifest
granite-4.1-30b-4bit.json · .minisig
Manifest sha256
dbba4942bafd32d03ea36bafcf74f2b6515301d69d75152c66c8232188009af0
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:14 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/granite-4.1-30b-4bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/granite-4.1-30b-4bit.json.minisig $ minisign -Vm granite-4.1-30b-4bit.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-4.1-30b · 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 mlx-community/granite-4.1-30b-4bit
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. granite-4.1-30b-4bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/granite-4.1-30b-4bit

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