alt.freeweights.granite / granite-4.1-30b-fp8

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

granite-4.1-30b-fp8

Date: 2026-11-15Commit: aa99937Signed: 2DC28CC7B26A283B ✓

Text generation model with 29.3B parameters. Safetensors weights, 30.1 GB in all. Published by ibm-granite under Apache-2.0.

29.3B params30.1GBgranite-4.1-30b-fp8safetensorspermissive

FactsParams29.3BSize30.1 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive

$ fw get ibm-granite/granite-4.1-30b-fp8
# manifest sha256 cea4fdc6b7c1… · 30.1 GB · 20 files
$ fw verify ./granite-4.1-30b-fp8 ibm-granite/granite-4.1-30b-fp8

From sourceHosted (signed)ibm-granite/granite-4.1-30b-fp8Last check: 2026-11-15 05:06 UTC

Run at home Get help

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

Quantized of granite-4.1-30b.

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: 30.1 GB
Weights: 30.1 GB (safetensors)
Parameters: 29.3B
Formats: safetensors
Task: text generation
License: Apache-2.0 (permissive)
Files: 20, 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-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

Badge	Host	Last check	Result
From source	huggingface.co	2026-11-15 05:06 UTC	passed

Model card

From the publisher at commit aa99937. Shown as plain text with links; images open at the publisher.

Granite-4.1-30B (FP8)#

Note. This repository contains the FP8 version of 4.1-30B.

Please refer to the the original instruct model's model card for additional details: https://huggingface.co/ibm-granite/granite-4.1-30b

Files

20 files · 30.1 GBWeights 30.1 GB (safetensors). Sizes and sha256 from the signed manifest.

Hide all 20 files with their sha256

File	Size	sha256
.gitattributes	1.52 KB	11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
README.md	376 B	a0a5fd460d570ff76d9156172efe47cbe844c3f1bd361f731bf02e739f2ae402
chat_template.jinja	6.10 KB	fed2756d2d24e127b951dcf139d0b03ab7db8ef23a456128ebc9c2db4901d476
config.json	2.13 KB	356dc2a865a43c5d3297414bea876470090089743daa68730ed5f036a4bf1b13
generation_config.json	147 B	eef72a0268cb044a95782d1d9dcf35105890e081f5a3dbb4004cf1bd70b916a6
merges.txt	917 KB	b6fe424e334903f7fb84d3a106d9730455f4744b9fe3c21ee136d97a00e72502
model-00001-of-00007.safetensors	4.87 GB	02cdba0d82a6ba417ceaf1b3d0a191cfb27eaeebabb82742a2d65e525923847c
model-00002-of-00007.safetensors	4.89 GB	5def3b7f316ab206ce67da2eb7feb8387d2c2a570b828a12a9684dacf15ad965
model-00003-of-00007.safetensors	4.89 GB	9bdefeb3ee59e92e47490be595f1d7adb1f0743e06495d24c0ed92f422472653
model-00004-of-00007.safetensors	4.89 GB	d7e094fb05b6b127c5d111be83e7413e7781e5717ddedfde1e660a1d293d0058
model-00005-of-00007.safetensors	4.89 GB	bbdb35a492d553cea69d16c3e7c0bc0ff66e3a1ddd9fd9692d505313573c5277
model-00006-of-00007.safetensors	4.85 GB	6670367b39ffe7d7d0bbcd1796a99a1a99fa25ac3cc0fbd5ef1ad82ecd6520f7
model-00007-of-00007.safetensors	822 MB	666fb265c7bf4c442eae6a7f3d40dbc92783f6e6ab955a331b613ec50358eac4
model.safetensors.index.json	86.9 KB	6caced4f441c990e451cad02fb9626a80d4eca643c6d8c42458e0d2f3b921380
model.sig	12.0 KB	c381d017e7dbe999c6b1160b36127c9eb18564d8a3c2a9645942d22391019d62
recipe.yaml	176 B	202b71abfb88a3e1bddc2f79f4c3742171af6bd60c214573c4610b3b1817c91f
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
aa99937ea2 pinned now	2026-11-15 05:06 UTC	20 files · 30.1 GB

Use it

$ fw get ibm-granite/granite-4.1-30b-fp8
# manifest sha256 cea4fdc6b7c1… · 30.1 GB · 20 files
$ fw verify ./granite-4.1-30b-fp8 ibm-granite/granite-4.1-30b-fp8

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-4.1-30b-fp8.json --dir ./granite-4.1-30b-fp8
$ python3 fw.py verify ./granite-4.1-30b-fp8 ./ibm-granite__granite-4.1-30b-fp8.json

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

$ HF_ENDPOINT=https://freeweights.allternit.com hf download ibm-granite/granite-4.1-30b-fp8 --revision aa99937ea2b8acf605601a0789ad2daea26b4c7e --local-dir ./granite-4.1-30b-fp8

transformersLoad the weights in Python.

import os
os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com"
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("ibm-granite/granite-4.1-30b-fp8", revision="aa99937ea2b8acf605601a0789ad2daea26b4c7e")
model = AutoModelForCausalLM.from_pretrained("ibm-granite/granite-4.1-30b-fp8", revision="aa99937ea2b8acf605601a0789ad2daea26b4c7e", device_map="auto")

vLLMServe an OpenAI-compatible API.

$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve ibm-granite/granite-4.1-30b-fp8 --revision aa99937ea2b8acf605601a0789ad2daea26b4c7e

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: a0a5fd460d570ff76d9156172efe47cbe844c3f1bd361f731bf02e739f2ae402
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-4.1-30b-fp8Date: 2026-11-15Commit: aa99937Signed: 2DC28CC7B26A283B ✓

Upstream: ibm-granite/granite-4.1-30b-fp8
Pinned commit: aa99937ea2b8acf605601a0789ad2daea26b4c7e
Manifest: granite-4.1-30b-fp8.json · .minisig
Manifest sha256: cea4fdc6b7c1821edf9ff4acaf17265b77e8c154122c724ba7992936a2c64406
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-15 05:06 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/ibm-granite/granite-4.1-30b-fp8.json
$ curl -O https://freeweights.allternit.com/manifests/ibm-granite/granite-4.1-30b-fp8.json.minisig
$ minisign -Vm granite-4.1-30b-fp8.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 ibm-granite/granite-4.1-30b-fp8

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-fp8.json. Provenance. Takedown history: none.

Source

huggingface.co/ibm-granite/granite-4.1-30b-fp8

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-4.1-30b-fp8

Works with

Runs with

Fine-tune with

Convert with

Evaluate with

Scan with

Works with

Overview

Model card

Granite-4.1-30B (FP8)#

Files

Use it

License

Provenance

How to verify

Model tree

Related models