From: <huggingface.co/mlx-community> Newsgroups: alt.freeweights.abliteratedSubject: Qwen3-8B-abliterated-v2-mxfp4 Date: 2026-11-15Commit: 0310576Signed: 2DC28CC7B26A283B ✓ Text generation model with 8.2B parameters. Safetensors weights, 4.36 GB in all. Published by mlx-community under Apache-2.0. Changed from the base model.
8.2B params 4.36 GB Qwen3-8B-abliterated-v2-mxfp4 safetensors permissive Facts Params 8.2B Size 4.36 GB Formats safetensors Task text generation License Apache-2.0 permissive
fw
$ fw get mlx-community/Qwen3-8B-abliterated-v2-mxfp4
# manifest sha256 b559bae51a1b… · 4.36 GB · 9 files
$ fw verify ./Qwen3-8B-abliterated-v2-mxfp4 mlx-community/Qwen3-8B-abliterated-v2-mxfp4Hosted (signed) mlx-community/Qwen3-8B-abliterated-v2-mxfp4 Last check: 2026-11-15 05:12 UTC
Get help: custom fine-tune or private deploy. We review your setup before we quote.
Quantized of Huihui-Qwen3-8B-abliterated-v2 .
Works with
Runs with Ranked by fit to this model (safetensors), then by GitHub stars.
Show all 24 Fine-tune with Show all 29
Overview
Size 4.36 GB
Weights 4.35 GB (safetensors)
Parameters 8.2B
Formats safetensors
Task text generation
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 huihui-ai/Huihui-Qwen3-8B-abliterated-v2 by the uploader. Read the model card at the source for the method and the layers touched.
Base model: huihui-ai/Huihui-Qwen3-8B-abliterated-v2
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 huggingface.co 2026-11-15 05:12 UTC passed
Model card From the publisher at commit
0310576 . Shown as plain text with links; images open at the publisher.
This model mlx-community/Qwen3-8B-abliterated-v2-mxfp4 was converted to MLX format from huihui-ai/Huihui-Qwen3-8B-abliterated-v2 using mlx-lm version 0.29.0 .
Use with mlx#
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Qwen3-8B-abliterated-v2-mxfp4")
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 9 files · 4.36 GB Weights 4.35 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 1.04 KB e7a5cc97116baf87719cbf3de33f5651a58868f883c4a8557e23cee9f373d871 chat_template.jinja 4.12 KB 87a2728cb8dc9fe424d624542f6060ec05a1d285ebbec578bb078900e33396b5 config.json 989 B f9c5c284514c20e32706a2f4d2a5dd6fee29ad6f8ae7bc1a681f7b7269987c6b generation_config.json 227 B 50a126529f5afe9dbc3701d30ef53759eee2b53d0285f7d42293cc1e54c645e7 model.safetensors 4.35 GB 359eda6cad4d513642ef52ac9eec1bac141f9b41e0125569b95f1317093e7491 model.safetensors.index.json 46.3 KB 630c03b73bc8fbd97b6c7b62a2d3dbf1967cfc32e8f758a9d61bc74062c09445 tokenizer.json 11.4 MB 05d47c87966b4db779200053de490f89936ed529f8ab889244e271630715fcfe tokenizer_config.json 1.02 KB ad76b1bb4ae49da6c3af6549208ea404714f731fa05aecce9ab880caf20f5b62
Versions Each time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commit Date Contents 0310576b3a pinned now 2026-11-15 05:12 UTC 9 files · 4.36 GB
Use it fw
$ fw get mlx-community/Qwen3-8B-abliterated-v2-mxfp4
# manifest sha256 b559bae51a1b… · 4.36 GB · 9 files
$ fw verify ./Qwen3-8B-abliterated-v2-mxfp4 mlx-community/Qwen3-8B-abliterated-v2-mxfp4fw.py Checks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/Qwen3-8B-abliterated-v2-mxfp4.json --dir ./Qwen3-8B-abliterated-v2-mxfp4
$ python3 fw.py verify ./Qwen3-8B-abliterated-v2-mxfp4 ./mlx-community__Qwen3-8B-abliterated-v2-mxfp4.jsonhf The Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT =https://freeweights.allternit.com hf download mlx-community/Qwen3-8B-abliterated-v2-mxfp4 --revision 0310576b3aa0daf9d8ad6ec370ff2c545ef02194 --local-dir ./Qwen3-8B-abliterated-v2-mxfp4transformers Load 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/Qwen3-8B-abliterated-v2-mxfp4", revision="0310576b3aa0daf9d8ad6ec370ff2c545ef02194")
model = AutoModelForCausalLM.from_pretrained("mlx-community/Qwen3-8B-abliterated-v2-mxfp4", revision="0310576b3aa0daf9d8ad6ec370ff2c545ef02194", device_map="auto")vLLM Serve an OpenAI-compatible API.
$ HF_ENDPOINT =https://freeweights.allternit.com vllm serve mlx-community/Qwen3-8B-abliterated-v2-mxfp4 --revision 0310576b3aa0daf9d8ad6ec370ff2c545ef02194License 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 e7a5cc97116baf87719cbf3de33f5651a58868f883c4a8557e23cee9f373d871 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: <huggingface.co/mlx-community> Newsgroups: alt.freeweights.abliteratedSubject: Qwen3-8B-abliterated-v2-mxfp4 Date: 2026-11-15Commit: 0310576Signed: 2DC28CC7B26A283B ✓ How to verify
$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3-8B-abliterated-v2-mxfp4.json
$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3-8B-abliterated-v2-mxfp4.json.minisig
$ minisign -Vm Qwen3-8B-abliterated-v2-mxfp4.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 No model in the catalog names this one as its parent.
Get it
$ HF_ENDPOINT =https://freeweights.allternit.com hf download mlx-community/Qwen3-8B-abliterated-v2-mxfp4Open in Freeweights Studio Pull, verify and run it in the Allternit app on Desktop, web or phone.
9.4B params 19.3 GB DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic safetensors permissive Facts Params 9.4B Size 19.3 GB Formats safetensors Task text generation License Apache-2.0 permissive flip From: xtools-at <huggingface.co/xtools-at> Subject: DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic 9B params 8.22 GB DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-4bit safetensors permissive Facts Params 9B Size 8.22 GB Formats safetensors Task image text to text License Apache-2.0 permissive flip From: <huggingface.co/mlx-community> Subject: DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-4bit 25.8B params 10.2 GB gemma-4-26B-A4B-it-heretic-msq-2.6bit safetensors permissive Facts Params 25.8B Size 10.2 GB Formats safetensors Task image text to text License Apache-2.0 permissive flip From: <huggingface.co/mlx-community> Subject: gemma-4-26B-A4B-it-heretic-msq-2.6bit 31.3B params 62.6 GB gemma-4-31B-it-heretic safetensors permissive Facts Params 31.3B Size 62.6 GB Formats safetensors Task image text to text License Apache-2.0 permissive flip From: coder3101 <huggingface.co/coder3101> Subject: gemma-4-31B-it-heretic 30.7B params 62.1 GB gemma-4-31B-it-SDFT-Heretic-RP gguf safetensors permissive Facts Params 30.7B Size 62.1 GB Formats gguf, safetensors Task not tagged License Apache-2.0 permissive flip From: Ilya626 <huggingface.co/Ilya626> Subject: gemma-4-31B-it-SDFT-Heretic-RP 31.3B params 62.6 GB gemma-4-31B-it-uncensored-heretic safetensors permissive Facts Params 31.3B Size 62.6 GB Formats safetensors Task image text to text License Apache-2.0 permissive flip From: llmfan46 <huggingface.co/llmfan46> Subject: gemma-4-31B-it-uncensored-heretic
mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.abliteratedSubject: 
