alt.freeweights.granite / granite-4.1-3b-4bit

From:

mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.graniteSubject:

granite-4.1-3b-4bit

Date: 2026-11-15Commit: b1b476bSigned: 2DC28CC7B26A283B ✓

Text generation model with 3.4B parameters. Safetensors weights, 2.13 GB in all. Published by mlx-community under Apache-2.0.

3.4B params

2.13GBgranite-4.1-3b-4bitsafetensorspermissive

FactsParams3.4BSize2.13 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive

$ fw get mlx-community/granite-4.1-3b-4bit
# manifest sha256 bac734558b3b… · 2.13 GB · 9 files
$ fw verify ./granite-4.1-3b-4bit mlx-community/granite-4.1-3b-4bit

From sourceHosted (signed)mlx-community/granite-4.1-3b-4bitLast check: 2026-11-15 05:04 UTC

Run at home Get help

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

Quantized of granite-4.1-3b.

Works with

Run24 Fine-tune29 Convert15 Evaluate13 Scan13 Apps58

Runs with

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

vLLM exo Text Generation WebUI

SGLang MLC LLM KTransformers LMCache Xinference LMDeploy mistral.rs Mooncake FlashInfer

Show all 24

AIBrix fastllm ExLlamaV3

Transformers LocalAI tinygrad gpu-unlock Triton Inference Server BentoML CTranslate2 ExLlamaV2 LitServe

Convert with

mergekit TensorRT Model Optimizer

LLM Compressor Neural Compressor AutoRound AQLM GPTQModel ONNX Core ML Tools ExecuTorch

Show all 15

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

Show all 13

picklescan

Overview Model card Files Use it License Provenance Model tree

Overview

Size: 2.13 GB
Weights: 2.13 GB (safetensors)
Parameters: 3.4B
Formats: safetensors
Task: text generation
License: Apache-2.0 (permissive)
Files: 9, 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-4.1-3b

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 05:04 UTC	passed

Model card

From the publisher at commit b1b476b. Shown as plain text with links; images open at the publisher.

mlx-community/granite-4.1-3b-4bit#

This model mlx-community/granite-4.1-3b-4bit was converted to MLX format from ibm-granite/granite-4.1-3b 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-4.1-3b-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

9 files · 2.13 GBWeights 2.13 GB (safetensors). Sizes and sha256 from the signed manifest.

Hide all 9 files with their sha256

File	Size	sha256
.gitattributes	1.52 KB	11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
README.md	896 B	5ed52735204b26574ecfba4bd6ea085d8b4bf905ab482d2b166315475bac76fd
chat_template.jinja	6.10 KB	fed2756d2d24e127b951dcf139d0b03ab7db8ef23a456128ebc9c2db4901d476
config.json	1.07 KB	4e7692aa044e9faefc7ef89a09844f4db1d038e08ee9862eaf34cae209c0651f
generation_config.json	147 B	9117fb03fed79dbb459373edeef9a3eec966bce52a1842e03a6716e83117f0d1
model.safetensors	2.13 GB	cff9d052cc3c68ea66b3d364788eb96fca2be82868d9ad92bd968e73b125194d
model.safetensors.index.json	65.3 KB	7e986d9c490d1ae27e1acbc2d3227ed90c5e5d38872813fd7a8591f073b30165
tokenizer.json	7.15 MB	24665f2815ee47aba521e4710bfc52f8ca045a552ec3f60925cce5e0edecb657
tokenizer_config.json	418 B	fb2f8b5d9980cc7c2e4aa3361b34d3f43c6ff94f675276ac2e32fb2e9b751594

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

Upstream commit	Date	Contents
b1b476b5a1 pinned now	2026-11-15 05:04 UTC	9 files · 2.13 GB

Use it

$ fw get mlx-community/granite-4.1-3b-4bit
# manifest sha256 bac734558b3b… · 2.13 GB · 9 files
$ fw verify ./granite-4.1-3b-4bit mlx-community/granite-4.1-3b-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-4.1-3b-4bit.json --dir ./granite-4.1-3b-4bit
$ python3 fw.py verify ./granite-4.1-3b-4bit ./mlx-community__granite-4.1-3b-4bit.json

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

$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/granite-4.1-3b-4bit --revision b1b476b5a17c46b7d6cd663b4a8ed44b66720aef --local-dir ./granite-4.1-3b-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-4.1-3b-4bit", revision="b1b476b5a17c46b7d6cd663b4a8ed44b66720aef")
model = AutoModelForCausalLM.from_pretrained("mlx-community/granite-4.1-3b-4bit", revision="b1b476b5a17c46b7d6cd663b4a8ed44b66720aef", device_map="auto")

vLLMServe an OpenAI-compatible API.

$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/granite-4.1-3b-4bit --revision b1b476b5a17c46b7d6cd663b4a8ed44b66720aef

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: 5ed52735204b26574ecfba4bd6ea085d8b4bf905ab482d2b166315475bac76fd
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-4.1-3b-4bitDate: 2026-11-15Commit: b1b476bSigned: 2DC28CC7B26A283B ✓

Upstream: mlx-community/granite-4.1-3b-4bit
Pinned commit: b1b476b5a17c46b7d6cd663b4a8ed44b66720aef
Manifest: granite-4.1-3b-4bit.json · .minisig
Manifest sha256: bac734558b3b0ef1ce25eab00e6de236e6a9e1e5da74a27a5c3e7525b6d9e32b
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-15 05:04 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/granite-4.1-3b-4bit.json
$ curl -O https://freeweights.allternit.com/manifests/mlx-community/granite-4.1-3b-4bit.json.minisig
$ minisign -Vm granite-4.1-3b-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-4.1-3b · 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-4.1-3b-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-4.1-3b-4bit.json. Provenance. Takedown history: none.

Source

huggingface.co/mlx-community/granite-4.1-3b-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

granite-4.1-3b-4bit

Works with

Runs with

Fine-tune with

Convert with

Evaluate with

Scan with

Works with

Overview

Model card

mlx-community/granite-4.1-3b-4bit#

Use with mlx#

Files

Use it

License

Provenance

How to verify

Model tree

Related models