alt.freeweights.abliterated / Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-4bit

From:

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

Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-4bit

Date: 2026-11-15Commit: a0cd614Signed: 2DC28CC7B26A283B ✓

Image text to text model with 4.5B parameters. Safetensors weights, 3.05 GB in all. Published by mlx-community under Apache-2.0. Changed from the base model.

4.5B params

3.05GBHuihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-4bitsafetensorspermissive

FactsParams4.5BSize3.05 GBFormatssafetensorsTaskimage text to textLicenseApache-2.0From sourcepermissive

$ fw get mlx-community/Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-4bit
# manifest sha256 b3e5f4ff4134… · 3.05 GB · 9 files
$ fw verify ./Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-4bit mlx-community/Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-4bit

From sourceHosted (signed)mlx-community/Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-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 Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled.

Works with

Run23 Fine-tune29 Convert15 Evaluate13 Scan13 Apps62

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 23

AIBrix fastllm ExLlamaV3

Transformers LocalAI tinygrad 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: 3.05 GB
Weights: 3.03 GB (safetensors)
Parameters: 4.5B
Formats: safetensors
Task: image text to text
License: Apache-2.0 (permissive)
Files: 9, 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 Jackrong/Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled by the uploader. Read the model card at the source for the method and the layers touched.

Base model: Jackrong/Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled

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 a0cd614. Shown as plain text with links; images open at the publisher.

mlx-community/Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-4bit#

This model was converted to MLX format from huihui-ai/Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated using mlx-vlm version 0.4.0. Refer to the original model card for more details on the model.

Use with mlx#

pip install -U mlx-vlm

python -m mlx_vlm.generate --model mlx-community/Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-4bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>

Files

9 files · 3.05 GBWeights 3.03 GB (safetensors). Sizes and sha256 from the signed manifest.

Hide all 9 files with their sha256

File	Size	sha256
.gitattributes	1.57 KB	34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md	965 B	413624551803f0acc8aa455483dd7f57c4735cc08b5336331bc38332dc17fd5c
chat_template.jinja	4.05 KB	0800c03b537cb0d60244f37ac6d717b06c42c4828a40853b1f9853791f9afdae
config.json	3.65 KB	23323f38178e6d39316173eb78bdaf3982f9542e3cc6dc540d920bfc4da2baeb
model.safetensors	3.03 GB	a8b882de33e05db3d1e863a6b2ff6e42d7d5b991eeae1e81b25095c28b9f5e92
model.safetensors.index.json	102 KB	52e534c41f7b97708329c85f762e5882bf48bd5955a422c6ae74eba321e6048a
processor_config.json	1.30 KB	14932921ca485d458a04dafd8069fbb0a4505622a48208d19ed247115801385b
tokenizer.json	20.0 MB	87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
tokenizer_config.json	1.17 KB	1b448e2a25f75db98bd0ae7ba191de9caaf79f07ec4c454045a33d6ba9b481a7

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

Upstream commit	Date	Contents
a0cd614060 pinned now	2026-11-15 05:07 UTC	9 files · 3.05 GB

Use it

$ fw get mlx-community/Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-4bit
# manifest sha256 b3e5f4ff4134… · 3.05 GB · 9 files
$ fw verify ./Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-4bit mlx-community/Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-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/Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-4bit.json --dir ./Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-4bit
$ python3 fw.py verify ./Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-4bit ./mlx-community__Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-4bit.json

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

$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-4bit --revision a0cd61406062a7bee31fc995a806fdb876f318ed --local-dir ./Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-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/Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-4bit", revision="a0cd61406062a7bee31fc995a806fdb876f318ed")
model = AutoModelForImageTextToText.from_pretrained("mlx-community/Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-4bit", revision="a0cd61406062a7bee31fc995a806fdb876f318ed", device_map="auto")

vLLMServe an OpenAI-compatible API.

$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-4bit --revision a0cd61406062a7bee31fc995a806fdb876f318ed

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: 413624551803f0acc8aa455483dd7f57c4735cc08b5336331bc38332dc17fd5c
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: Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-4bitDate: 2026-11-15Commit: a0cd614Signed: 2DC28CC7B26A283B ✓

Upstream: mlx-community/Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-4bit
Pinned commit: a0cd61406062a7bee31fc995a806fdb876f318ed
Manifest: Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-4bit.json · .minisig
Manifest sha256: b3e5f4ff413490bb959c651ffd164bfcab111eb01536f70cefa15148c0d30687
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/Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-4bit.json
$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-4bit.json.minisig
$ minisign -Vm Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-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

Jackrong/Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled · 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/Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-4bit

Open in Freeweights Studio

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

Signed manifest

minisign, key 2DC28CC7B26A283B. Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-4bit.json. Provenance. Takedown history: none.

Source

huggingface.co/mlx-community/Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-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

Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-4bit

Works with

Runs with

Fine-tune with

Convert with

Evaluate with

Scan with

Works with

Overview

Model card

mlx-community/Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-4bit#

Use with mlx#

Files

Use it

License

Provenance

How to verify

Model tree

Related models