alt.freeweights.granite / granite-4.0-h-micro-4bit

From:

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

granite-4.0-h-micro-4bit

Date: 2026-11-15Commit: 0a29e17Signed: 2DC28CC7B26A283B ✓

Text generation model with 3.2B parameters. Safetensors weights, 1.81 GB in all. Published by mlx-community under Apache-2.0.

3.2B params

1.81GBgranite-4.0-h-micro-4bitsafetensorspermissive

FactsParams3.2BSize1.81 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive

$ fw get mlx-community/granite-4.0-h-micro-4bit
# manifest sha256 0a932fda4fae… · 1.81 GB · 12 files
$ fw verify ./granite-4.0-h-micro-4bit mlx-community/granite-4.0-h-micro-4bit

From sourceHosted (signed)mlx-community/granite-4.0-h-micro-4bitLast check: 2026-11-15 05:07 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-micro.

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: 1.81 GB
Weights: 1.80 GB (safetensors)
Parameters: 3.2B
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-4.0-h-micro

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 05:07 UTC	passed

Model card

From the publisher at commit 0a29e17. Shown as plain text with links; images open at the publisher.

mlx-community/granite-4.0-h-micro-4bit#

This model mlx-community/granite-4.0-h-micro-4bit was converted to MLX format from ibm-granite/granite-4.0-h-micro using mlx-lm version 0.28.2.

Use with mlx#

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/granite-4.0-h-micro-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
    )

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

Files

12 files · 1.81 GBWeights 1.80 GB (safetensors). Sizes and sha256 from the signed manifest.

Hide all 12 files with their sha256

File	Size	sha256
.gitattributes	1.52 KB	11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
README.md	910 B	cf19aca4f117a373ffd680711c3d567362b2a7936e92454ca34428e67d10a548
chat_template.jinja	6.10 KB	fed2756d2d24e127b951dcf139d0b03ab7db8ef23a456128ebc9c2db4901d476
config.json	2.26 KB	d42f4e62696734e58fc57f733c3ca83ebb5a21f774de16d8b00010d36b08c98e
generation_config.json	147 B	7c04cb9d2ba771f7528fba5a7104999cdaf7566d02b5fbd58472829f62716177
merges.txt	917 KB	b6fe424e334903f7fb84d3a106d9730455f4744b9fe3c21ee136d97a00e72502
model.safetensors	1.80 GB	573654ce0613804f3e0e5ec692b039f907f13c88273dc08993b9adbeb04428f1
model.safetensors.index.json	62.8 KB	7506c4d473813c56dbe385ed0a243e497c5eec18d52e15d3e6efb317bf00e1f0
special_tokens_map.json	579 B	c08676c49fd7969a3130f72be6d4bf34da66aa484a6e21dffe359893a1bd5f2e
tokenizer.json	7.15 MB	e2bad66439538cb4d5a7580680932432ed9ece9d3b8577e675512bdf11599253
tokenizer_config.json	17.7 KB	a5ec5daab12ba090a90f3dd169c8f9c275557013a87b9c1258dc7cb497a35c86
vocab.json	1.61 MB	8af71076de8b0b626eed0f4c984faf0a7c062479164b2a31308a948524d4f69c

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

Upstream commit	Date	Contents
0a29e17503 pinned now	2026-11-15 05:07 UTC	12 files · 1.81 GB

Use it

$ fw get mlx-community/granite-4.0-h-micro-4bit
# manifest sha256 0a932fda4fae… · 1.81 GB · 12 files
$ fw verify ./granite-4.0-h-micro-4bit mlx-community/granite-4.0-h-micro-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-4.0-h-micro-4bit.json --dir ./granite-4.0-h-micro-4bit
$ python3 fw.py verify ./granite-4.0-h-micro-4bit ./mlx-community__granite-4.0-h-micro-4bit.json

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

$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/granite-4.0-h-micro-4bit --revision 0a29e17503da7de371af61a0a532853810637627 --local-dir ./granite-4.0-h-micro-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-4.0-h-micro-4bit", revision="0a29e17503da7de371af61a0a532853810637627")
model = AutoModelForCausalLM.from_pretrained("mlx-community/granite-4.0-h-micro-4bit", revision="0a29e17503da7de371af61a0a532853810637627", device_map="auto")

vLLMServe an OpenAI-compatible API.

$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/granite-4.0-h-micro-4bit --revision 0a29e17503da7de371af61a0a532853810637627

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: cf19aca4f117a373ffd680711c3d567362b2a7936e92454ca34428e67d10a548
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-4.0-h-micro-4bitDate: 2026-11-15Commit: 0a29e17Signed: 2DC28CC7B26A283B ✓

Upstream: mlx-community/granite-4.0-h-micro-4bit
Pinned commit: 0a29e17503da7de371af61a0a532853810637627
Manifest: granite-4.0-h-micro-4bit.json · .minisig
Manifest sha256: 0a932fda4fae3af133a64db2e47d17d15ff1bdc80bb63143f2dd01eafd79f1f2
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-15 05:07 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/granite-4.0-h-micro-4bit.json
$ curl -O https://freeweights.allternit.com/manifests/mlx-community/granite-4.0-h-micro-4bit.json.minisig
$ minisign -Vm granite-4.0-h-micro-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-4.0-h-micro · 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-4.0-h-micro-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-4.0-h-micro-4bit.json. Provenance. Takedown history: none.

Source

huggingface.co/mlx-community/granite-4.0-h-micro-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-4.0-h-micro-4bit

Works with

Runs with

Fine-tune with

Convert with

Evaluate with

Scan with

Works with

Overview

Model card

mlx-community/granite-4.0-h-micro-4bit#

Use with mlx#

Files

Use it

License

Provenance

How to verify

Model tree

Related models