CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.abliterated / Huihui-Qwen3.6-27B-abliterated
From: huihui-ai <huggingface.co/huihui-ai>Newsgroups: alt.freeweights.abliteratedSubject:

Huihui-Qwen3.6-27B-abliterated

Date: 2026-11-15Commit: 27502c8Signed: 2DC28CC7B26A283B ✓

Image text to text model with 27.8B parameters. Safetensors weights, 55.6 GB in all. Published by huihui-ai under Apache-2.0. Changed from the base model.

27.8B params55.6GBHuihui-Qwen3.6-27B-abliteratedsafetensorspermissive
FactsParams27.8BSize55.6 GBFormatssafetensorsTaskimage text to textLicenseApache-2.0From sourcepermissive
$ fw get huihui-ai/Huihui-Qwen3.6-27B-abliterated
# manifest sha256 4d975a75b415… · 55.6 GB · 29 files
$ fw verify ./Huihui-Qwen3.6-27B-abliterated huihui-ai/Huihui-Qwen3.6-27B-abliterated
From sourceHosted (signed)huihui-ai/Huihui-Qwen3.6-27B-abliteratedLast check: 2026-11-15 03:25 UTC
Run at homeGet help

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

Fine-tune of Qwen3.6-27B.

Works with

Run23Fine-tune29Convert15Evaluate13Scan13Apps62
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
55.6 GB
Weights
55.6 GB (safetensors)
Parameters
27.8B
Formats
safetensors
Task
image text to text
License
Apache-2.0 (permissive)
Files
29, each with a sha256
Publisher
huihui-ai
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 Qwen/Qwen3.6-27B by the uploader. Read the model card at the source for the method and the layers touched.

Base model: Qwen/Qwen3.6-27B

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 03:25 UTCpassed

Model card

From the publisher at commit 27502c8. Shown as plain text with links; images open at the publisher.

huihui-ai/Huihui-Qwen3.6-27B-abliterated#

This is an uncensored version of Qwen/Qwen3.6-27B created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.

ollama#

Please use the latest version of ollama

You can use huihui_ai/qwen3.6-abliterated:27b directly, 

ollama run huihui_ai/qwen3.6-abliterated:27b
Usage Warnings#
  • Risk of Sensitive or Controversial Outputs: This model’s safety filtering has been significantly reduced, potentially generating sensitive, controversial, or inappropriate content. Users should exercise caution and rigorously review generated outputs.
  • Not Suitable for All Audiences: Due to limited content filtering, the model’s outputs may be inappropriate for public settings, underage users, or applications requiring high security.
  • Legal and Ethical Responsibilities: Users must ensure their usage complies with local laws and ethical standards. Generated content may carry legal or ethical risks, and users are solely responsible for any consequences.
  • Research and Experimental Use: It is recommended to use this model for research, testing, or controlled environments, avoiding direct use in production or public-facing commercial applications.
  • Monitoring and Review Recommendations: Users are strongly advised to monitor model outputs in real-time and conduct manual reviews when necessary to prevent the dissemination of inappropriate content.
  • No Default Safety Guarantees: Unlike standard models, this model has not undergone rigorous safety optimization. huihui.ai bears no responsibility for any consequences arising from its use.
Donation#
Your donation helps us continue our further development and improvement, a cup of coffee can do it.#
  • bitcoin:
  bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge
  • Support our work on Ko-fi!

Files

29 files · 55.6 GBWeights 55.6 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 29 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
LICENSE11.3 KB50cbab8a892c5f2993b8c7351a99182507472def3b1374558308605d99b86b32
README.md2.46 KB19b3b518992e63654796fda811705459fc445ab831a02dd771e663af6ba082cd
chat_template.jinja7.76 KBe84f32a23fdda27689f868aa4a1a5621f41133e51a48d7f3efcbea2839574259
config.json4.31 KB69db4eb7196bc8190813231b3018ca05d8c2e3abc7b1af19d55c157af44a9d9c
configuration.json51 B2d4464e2ead06bc9bc718c781309ad1e7baded626d66e8dcdc8b469ba185faf0
generation_config.json202 Be70c136c1b78ddc1fb0905bac8e733a4dc448d4f852a5dd75143fffc70be550e
merges.txt3.35 MBa9d356d7bdf1ef4949e3e748e95b8e10ad9d4e2e838eddc38a0a7b6b94d1db8d
model-00001-of-00015.safetensors3.97 GBfa762cd5d79c0c708cb2fddad2ff38c770692d75abf6592f19a9d5f84937881c
model-00002-of-00015.safetensors3.92 GB93f37141fb5bf205da06a5dcb671281e216510777c96c34a8d0c88fe6b792d4e
model-00003-of-00015.safetensors3.92 GB02279bcee836c0c06ac6cd48ef7ddb80573b7b74d75ae983fe3524c7ca899d9b
model-00004-of-00015.safetensors3.92 GB2165e678be19a7960ffc9ecbd3ad31cf6c1bcda4ac4ce7a4e97d65dd6b88db52
model-00005-of-00015.safetensors3.92 GB3bd4d70d4d9c6d22b4a8361380bcc2512c6994d6ad15cf0577381361d0a3c182
model-00006-of-00015.safetensors3.90 GB75707449bf0399994bf007b38598943b288193bfeb6559fa2dc26c38a2537821
model-00007-of-00015.safetensors3.99 GB1f14ce5d2996405ff6988efa44b7a35071230f8047fd851077b18ab135453987
model-00008-of-00015.safetensors3.88 GBd86981f9fded9a00f60d85270e4dbbc84dcc8a49fffe3e028ad59bdbb59c3da7
model-00009-of-00015.safetensors3.92 GB49aec55d16b90739df8adcc2ac586ac545a850564ef71f64a2c665354bc48c84
model-00010-of-00015.safetensors3.92 GB243b5c95251c814a54e176974f317e87e1181b9ee17534f80d26d4ab5a35607f
model-00011-of-00015.safetensors3.92 GBd23eea1ab532c5d798221e81ef1689dfc5e22673867e07195463dc85fd3d0265
model-00012-of-00015.safetensors3.92 GBcc7868e89018a24629be5841eb6ba8c3629ede77b62af9d036354226075cebf5
model-00013-of-00015.safetensors4.00 GB0867aab83d9d44105a3168630239098f7f3645687f8d78d425ab48aee5ea4e30
model-00014-of-00015.safetensors3.94 GB8361054c5ba438647b491f6f5457436374f636928b2606d5f3a81e5257376bcc
model-00015-of-00015.safetensors509 MBfa8ddc72895e9966666ba984434112a6ad23b3e225c77ffb9dfd1f882a665361
model.safetensors.index.json112 KBa8ad2c26fb707ff8c245806315b03e3b4b74595528492423af5dae0ce39b4d9b
preprocessor_config.json390 B27225450ac9c6529872ee1924fcb0962ff5634834f817040f444118116f4e516
tokenizer.json12.8 MB5f9e4d4901a92b997e463c1f46055088b6cca5ca61a6522d1b9f64c4bb81cb42
tokenizer_config.json16.7 KB5186f0defcd7f232382c7f0aebcd2252d073bb921ab240e407b7ae8745d2b29b
video_preprocessor_config.json385 B7768af27c1fafa9cc9011c1dc20067e03f8915e03b63504550e11d5066986d13
vocab.json6.72 MBce99b4cb2983d118806ce0a8b777a35b093e2000a503ebde25853284c9dfa003
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
27502c8717 pinned now2026-11-15 03:25 UTC29 files · 55.6 GB

Use it

$ fw get huihui-ai/Huihui-Qwen3.6-27B-abliterated
# manifest sha256 4d975a75b415… · 55.6 GB · 29 files
$ fw verify ./Huihui-Qwen3.6-27B-abliterated huihui-ai/Huihui-Qwen3.6-27B-abliterated
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/huihui-ai/Huihui-Qwen3.6-27B-abliterated.json --dir ./Huihui-Qwen3.6-27B-abliterated $ python3 fw.py verify ./Huihui-Qwen3.6-27B-abliterated ./huihui-ai__Huihui-Qwen3.6-27B-abliterated.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download huihui-ai/Huihui-Qwen3.6-27B-abliterated --revision 27502c8717fd5a2f8c0c77188c10c243fd4f672e --local-dir ./Huihui-Qwen3.6-27B-abliterated
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForImageTextToText, AutoProcessor processor = AutoProcessor.from_pretrained("huihui-ai/Huihui-Qwen3.6-27B-abliterated", revision="27502c8717fd5a2f8c0c77188c10c243fd4f672e") model = AutoModelForImageTextToText.from_pretrained("huihui-ai/Huihui-Qwen3.6-27B-abliterated", revision="27502c8717fd5a2f8c0c77188c10c243fd4f672e", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve huihui-ai/Huihui-Qwen3.6-27B-abliterated --revision 27502c8717fd5a2f8c0c77188c10c243fd4f672e
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
LICENSE
Text sha256
50cbab8a892c5f2993b8c7351a99182507472def3b1374558308605d99b86b32
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: huihui-ai <huggingface.co/huihui-ai>Newsgroups: alt.freeweights.abliteratedSubject: Huihui-Qwen3.6-27B-abliteratedDate: 2026-11-15Commit: 27502c8Signed: 2DC28CC7B26A283B ✓
Upstream
huihui-ai/Huihui-Qwen3.6-27B-abliterated
Pinned commit
27502c8717fd5a2f8c0c77188c10c243fd4f672e
Manifest
Huihui-Qwen3.6-27B-abliterated.json · .minisig
Manifest sha256
4d975a75b415de9e6adb1e495605f0ff2aeec4000b7103c7d70e0ff7090fd6ea
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 03:25 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/huihui-ai/Huihui-Qwen3.6-27B-abliterated.json $ curl -O https://freeweights.allternit.com/manifests/huihui-ai/Huihui-Qwen3.6-27B-abliterated.json.minisig $ minisign -Vm Huihui-Qwen3.6-27B-abliterated.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

Qwen/Qwen3.6-27B · this model is a finetune of it

No model in the catalog names this one as its parent.

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download huihui-ai/Huihui-Qwen3.6-27B-abliterated
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. Huihui-Qwen3.6-27B-abliterated.json. Provenance. Takedown history: none.
Source
huggingface.co/huihui-ai/Huihui-Qwen3.6-27B-abliterated

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