CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.abliterated / gemma-4-31B-it-uncensored-heretic-4bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.abliteratedSubject:

gemma-4-31B-it-uncensored-heretic-4bit

Date: 2026-11-15Commit: a4c7561Signed: 2DC28CC7B26A283B ✓

Image text to text model with 30.7B parameters. Safetensors weights, 17.3 GB in all. Published by mlx-community under Apache-2.0. Changed from the base model.

30.7B params17.3GBgemma-4-31B-it-uncensored-heretic-4bitsafetensorspermissive
FactsParams30.7BSize17.3 GBFormatssafetensorsTaskimage text to textLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/gemma-4-31B-it-uncensored-heretic-4bit
# manifest sha256 9b49c1e1b4f3… · 17.3 GB · 12 files
$ fw verify ./gemma-4-31B-it-uncensored-heretic-4bit mlx-community/gemma-4-31B-it-uncensored-heretic-4bit
From sourceHosted (signed)mlx-community/gemma-4-31B-it-uncensored-heretic-4bitLast check: 2026-11-15 05:04 UTC
Run at homeGet help

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

Quantized of gemma-4-31B-it-uncensored-heretic.

Works with

Run23Fine-tune29Convert15Evaluate13Scan13Apps62
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
17.3 GB
Weights
17.3 GB (safetensors)
Parameters
30.7B
Formats
safetensors
Task
image text to text
License
Apache-2.0 (permissive)
Files
12, each with a sha256
Publisher
mlx-community
Added
2026-11-15
Section
alt.freeweights.abliterated
Lineage

Changed from the base model. The uploader's repo is named abliterated: refusal behavior was removed from llmfan46/gemma-4-31B-it-uncensored-heretic by the uploader. Read the model card at the source for the method and the layers touched.

Base model: llmfan46/gemma-4-31B-it-uncensored-heretic

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 05:04 UTCpassed

Model card

From the publisher at commit a4c7561. Shown as plain text with links; images open at the publisher.

Use with mlx#

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/gemma-4-31B-it-uncensored-heretic-4bit")

prompt="hello"

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

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

Files

12 files · 17.3 GBWeights 17.3 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 12 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md802 Bc136cf0d8076e9203dcf44f799167f4e663ef8249eebf01ca82907febf38adb4
chat_template.jinja17.5 KB36e3a42e5cf14cd0020e72d92e1fdd9970f59b82170e421f0cbe1bb42bead3f0
config.json4.38 KBd251fa7e53ab63ee73578b1180351d0ff92dd00b727fe1ce5ee6e9d41b18714c
generation_config.json217 B857bd7826fd84d2522f7bd1d07d9b42bba84b715718984e931bc6d46b01c226c
model-00001-of-00004.safetensors5.37 GBea3de2445014c29cdb149b3d291b867a5814bd33b817ac1cb2b46532811bdd79
model-00002-of-00004.safetensors5.36 GBcd15486e0d8812631a2b2a08a8a9d60cb19f9cea1be3ffd391ae423ae3b88f80
model-00003-of-00004.safetensors5.37 GB736af71383a2ed965d066bcaedaad36ddb15f32a3f7d5b097aed37bbd8a2ee8d
model-00004-of-00004.safetensors1.17 GB0cbefa0792e60d29ee28cbfbc3cf7ca80c387b7a20cf5077e1488acf1cdd7e3b
model.safetensors.index.json167 KBf91e1cd26b0c9e95ece8a3e1afb5179eeee27578b2414345e574b53fea441c75
tokenizer.json32.2 MBcc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
tokenizer_config.json2.82 KBdf7a740ec729cd1530c6bf7e7182879dadd2d7f72ea1dad26fa0b3e230af5a00
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
a4c7561cc8 pinned now2026-11-15 05:04 UTC12 files · 17.3 GB

Use it

$ fw get mlx-community/gemma-4-31B-it-uncensored-heretic-4bit
# manifest sha256 9b49c1e1b4f3… · 17.3 GB · 12 files
$ fw verify ./gemma-4-31B-it-uncensored-heretic-4bit mlx-community/gemma-4-31B-it-uncensored-heretic-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/gemma-4-31B-it-uncensored-heretic-4bit.json --dir ./gemma-4-31B-it-uncensored-heretic-4bit $ python3 fw.py verify ./gemma-4-31B-it-uncensored-heretic-4bit ./mlx-community__gemma-4-31B-it-uncensored-heretic-4bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/gemma-4-31B-it-uncensored-heretic-4bit --revision a4c7561cc890307b95b473f8564634c3d598734a --local-dir ./gemma-4-31B-it-uncensored-heretic-4bit
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForImageTextToText, AutoProcessor processor = AutoProcessor.from_pretrained("mlx-community/gemma-4-31B-it-uncensored-heretic-4bit", revision="a4c7561cc890307b95b473f8564634c3d598734a") model = AutoModelForImageTextToText.from_pretrained("mlx-community/gemma-4-31B-it-uncensored-heretic-4bit", revision="a4c7561cc890307b95b473f8564634c3d598734a", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/gemma-4-31B-it-uncensored-heretic-4bit --revision a4c7561cc890307b95b473f8564634c3d598734a
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
c136cf0d8076e9203dcf44f799167f4e663ef8249eebf01ca82907febf38adb4
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.abliteratedSubject: gemma-4-31B-it-uncensored-heretic-4bitDate: 2026-11-15Commit: a4c7561Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/gemma-4-31B-it-uncensored-heretic-4bit
Pinned commit
a4c7561cc890307b95b473f8564634c3d598734a
Manifest
gemma-4-31B-it-uncensored-heretic-4bit.json · .minisig
Manifest sha256
9b49c1e1b4f3a10962b6c9936b1ef11089201a0edefc2616f6ccd7e0b59884fe
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/gemma-4-31B-it-uncensored-heretic-4bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/gemma-4-31B-it-uncensored-heretic-4bit.json.minisig $ minisign -Vm gemma-4-31B-it-uncensored-heretic-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

llmfan46/gemma-4-31B-it-uncensored-heretic · 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/gemma-4-31B-it-uncensored-heretic-4bit
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. gemma-4-31B-it-uncensored-heretic-4bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/gemma-4-31B-it-uncensored-heretic-4bit

Related models

All of alt.freeweights.abliterated →
From: xtools-at <huggingface.co/xtools-at>Subject: DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic
From: mlx-community <huggingface.co/mlx-community>Subject: DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-4bit
From: mlx-community <huggingface.co/mlx-community>Subject: gemma-4-26B-A4B-it-heretic-msq-2.6bit
From: coder3101 <huggingface.co/coder3101>Subject: gemma-4-31B-it-heretic
From: Ilya626 <huggingface.co/Ilya626>Subject: gemma-4-31B-it-SDFT-Heretic-RP
From: llmfan46 <huggingface.co/llmfan46>Subject: gemma-4-31B-it-uncensored-heretic