← back to catalog · registered 2026-08-22 13:56

HeYujie/Qwen3.5-35B-A3B-abliterated-GGUF

HeYujie Qwen 35B GGUF MoE multimodal second-order 262K ctx
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/HeYujie%2FQwen3.5-35B-A3B-abliterated-GGUF"
Response includes
  • classification m8
  • files 13
  • benchmarks 11 entries
  • hub_downloads_all_time 26,282
  • author_summary 2 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

Applied on top of direct removal inherited from the base model.
Confidence
MEDIUM
Inherited from base model
Why this label 3 signals
Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.
  • 'abliterated' in name/tags
  • is_gguf=1
  • assume M1 (base ablation) + M8 (GGUF quant) - default when producer unknown
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · lifetime
26K
2K last 30d - cooling
Likes
12
Model age
7mo ago
created 2026-02-28
Downloads over time
Now26.6K→from0↑0%
09.7K19.5K29.2K0 on Feb 2526.6K on Oct 11FebAprJunAugOct
Feb 25 → Oct 11 · 73 snapshots · spans 228 days

Benchmarks

Benchmark Score Source
Entertainment 0.6 UGI
Hazardous 1.2 UGI
Natural Intelligence 16.49 UGI
Political lean -14.4% UGI
Sensitive-Info 9.99 UGI
SocPol 1.3 UGI
UGI 31.66 UGI
Willingness (10) 7.5 UGI
W10-Adherence 8 UGI
W10-Direct 7 UGI
Writing 26.28 UGI

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

Metadata

License
apache-2.0
Quantizations
Q2_K Q3_K Q4 Q4_K Q5_K Q6_K Q8_0
Tags
transformers gguf abliterated uncensored llama-cpp quantized image-text-to-text base_model:huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated base_model:quantized:huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated license:apache-2.0 endpoints_compatible region:us

Related

Total size
221 GB
Files
13
Quantizations
8
Registered
2026-08-22 13:56
Last updated on HF
2026-03-05 06:43

Files by quantization

Q8_0 1 file 34.4 GB
Qwen3.5-35B-A3B-abliterated-Q8_0.gguf 34.4 GB 0742d0ee download
Q6_K 1 file 26.6 GB
Qwen3.5-35B-A3B-abliterated-Q6_K.gguf 26.6 GB 42650f13 download
Q5_K 1 file 23.1 GB
Qwen3.5-35B-A3B-abliterated-Q5_K_M.gguf 23.1 GB 1041d2dd download
Q4 2 files 38.7 GB
Qwen3.5-35B-A3B-abliterated-Q4_1.gguf 20.3 GB 8ddef47b download
Qwen3.5-35B-A3B-abliterated-Q4_0.gguf 18.4 GB 57805e19 download
Q4_K 2 files 38.2 GB
Qwen3.5-35B-A3B-abliterated-Q4_K_M.gguf 19.7 GB f26fea8d download
Qwen3.5-35B-A3B-abliterated-Q4_K_S.gguf 18.5 GB 60a656fd download
Q3_K 2 files 29.7 GB
Qwen3.5-35B-A3B-abliterated-Q3_K_M.gguf 15.6 GB 704a1e8b download
Qwen3.5-35B-A3B-abliterated-Q3_K_S.gguf 14.1 GB 8ed84d52 download
Q2_K 1 file 11.9 GB
Qwen3.5-35B-A3B-abliterated-Q2_K.gguf 11.9 GB 5db8222d download
Auxiliary files 3 files 18.4 GB
Qwen3.5-35B-A3B-abliterated-MXFP4_MOE.gguf 18.4 GB e1a03420 download
README.md 2.31 KB 2cbe6c05 download
.gitattributes 2.29 KB 7c39fd48 download

README current version from Hugging Face


license: apache-2.0
library_name: transformers
license_link: https://huggingface.co/Qwen/Qwen3.5-35B-A3B/blob/main/LICENSE
pipeline_tag: image-text-to-text
base_model: huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated
quantized: true
tags:

  • abliterated
  • uncensored
  • llama-cpp
  • gguf
  • quantized

Qwen3.5-35B-A3B-abliterated GGUF

This repository contains the GGUF quantized versions of huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated

huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated is an uncensored version of Qwen/Qwen3.5-35B-A3B 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.

Quantized Format

  • MXFP4_MOE
  • Q2_K
  • Q3_K_S
  • Q3_K_M
  • Q4_0
  • Q4_1
  • Q4_K_S
  • Q4_K_M
  • Q5_K_M
  • Q6_K
  • Q8_0

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.

README history 3 versions

The author's README evolved over time. Click a version to see its content at that point.

  1. 2026-03-05Update README.mdc584b122.3 KB
    Loading...
  2. 2026-02-28Update README.md71f13a32.3 KB
    Loading...
  3. 2026-02-28Create README.md3312b3c2.2 KB
    Loading...

Discussions 1 thread

  1. 2026-03-20Has anyone tried it? How was the effectopen2 💬#1
    Loading...
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Open in Abliteration