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

Jeethu/Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-BF16-PARO

Jeethu Qwen 3.5B multimodal second-order
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/Jeethu%2FQwen3.8-27B-AEON-ULTIMATE-UNCENSORED-BF16-PARO"
Response includes
  • classification m1
  • files 10
  • hub_downloads_all_time 414
  • author_summary 2 models
  • readme_text full
Try next
GET/models?author=Jeethu
All 2 models by Jeethu
 GET/models?family=qwen&method=m1
Sibling qwen models · same method
 GET/methods/m1
What "m1" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

No other method signals detected in this model.
Confidence
MEDIUM
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=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
How we label → About M1 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
414
221 last 30d - active
Likes
0
Model age
7w ago
created 2026-08-19
Downloads over time
Now470→from168↑180%
153269384500168 on Aug 19470 on Oct 11AugSepOct
Aug 19 → Oct 11 · 48 snapshots · spans 53 days

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.

AEON-7/Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-BF16↓ 13,753 this lineage
Jeethu/Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-BF16-PARO↓ 221

Metadata

License
apache-2.0
Languages
en zh multilingual
Tags
transformers safetensors qwen3_5 image-text-to-text 27b early-access draft abliterated abliterix aeon aeon-7 bf16

Related

Other by Jeethu
Huihui-gemma-4-E2B-it-abliterated-v2-PARO 14
Same base model
soyaakinohara/qwen3.8-27b-abliterated-3.69bpw-12GB-MTP.gguf 33K taurusduan/qwen3.8-27b-abliterated-3.69bpw-12GB-MTP.gguf 20K AEON-7/Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-NVFP4-MIXED 9K vcruz305/Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-GGUF 4K choppedgarlic/Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-4bit-MLX 3K
Total size
18.3 GB
Files
10
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-08-19 06:18
Source huggingface.co/Jeethu/Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-BF16-PARO ↗ Base model AEON-7/Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-BF16 →

Files by quantization

Auxiliary files 10 files 18.3 GB
model.safetensors 18.3 GB cd43847e download
tokenizer.json 19.1 MB 6f32ce20 download
chat_template.jinja 8.74 KB c0c686f9 download
config.json 3.72 KB 05d9a8c5 download
README.md 1.66 KB 5f6ecf1b download
.gitattributes 1.53 KB 52373fe2 download
tokenizer_config.json 1.10 KB d1a20cc3 download
preprocessor_config.json 390 B 2ea84a43 download
video_preprocessor_config.json 385 B 3ba673a5 download
generation_config.json 214 B 3f25ead4 download

README current version from Hugging Face

license: apache-2.0
language:

  • en
  • zh
  • multilingual
    library_name: transformers
    pipeline_tag: text-generation
    tags:
  • 27b
  • early-access
  • draft
  • abliterated
  • abliterix
  • aeon
  • aeon-7
  • bf16
  • bfloat16
  • chat
  • coding
  • conversational
  • function-calling
  • gated-deltanet
  • gdn
  • hybrid-attention
  • instruct
  • multimodal
  • qwen
  • qwen3
  • qwen3.8
  • reasoning
  • refusal-removed
  • thinking
  • tool-calling
  • uncensored
  • unfiltered
  • vision
  • vision-language
  • vllm
    base_model:
    • AEON-7/Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-BF16
      base_model_relation: quantized

Jeethu/Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-BF16-PARO

Pairwise Rotation Quantization for Efficient Reasoning LLM Inference

Paper Blog Models PyPI

ParoQuant is the state-of-the-art INT4 quantization for LLMs. It closes the accuracy gap with FP16 while running at near-AWQ speed. Supports NVIDIA GPUs (vLLM, Transformers) and Apple Silicon (MLX). For more information, see https://github.com/z-lab/paroquant.

Jeethu/Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-BF16-PARO is a 4-bit AEON-7/Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-BF16 quantized with ParoQuant.

README history 1 version

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

  1. 2026-08-19Upload folder using huggingface_hub6e5ca4d1.7 KB
    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.

Get the app Browse the catalog
Open in Abliteration