Skip to content

Search wahloon.net

Search models, news, guides and FAQs.

// catalog

Abliterated & uncensored models

A curated catalog of open-weight builds. Filter by base family, method, size, VRAM and quantization format. Every entry links to its Hugging Face repository.

Catalog updated Nov 18, 202618 models · 5 families
Method

Showing 18 of 18 models

Qwen35B-A3Bfeatured
Abliteration

Huihui-Qwen3.6-35B-A3B-abliterated-MTP

Qwen/Qwen3.6-35B-A3B

Highly popular MoE abliterated variant. Excellent quality-to-size ratio for the active parameter count.

Approx. VRAM
~21 GB (Q4)
License
Apache-2.0
Downloads
5.2M / 30d
#popular#qwen#moe#abliterated

updated Nov 15, 2026

Qwen27Bfeatured
Abliteration

Huihui-Qwen3.8-27B-abliterated

Qwen/Qwen3.8-27B

One of the most downloaded abliterated Qwen 3.8 27B builds. Strong general performance with significantly reduced refusals.

Approx. VRAM
~16–18 GB (Q4)
License
Apache-2.0
Downloads
4.5M / 30d
#popular#qwen#abliterated#gguf
ollama run huihui_ai/Qwen3.8-abliterated:27b

updated Nov 18, 2026

QwenFlash-Next
Abliteration

Qwen3.8-Flash-Next-GSQ-RCO-abliterated

Qwen/Qwen3.8-Flash-Next

Very high download count Flash-Next abliterated build. Strong for longer context and throughput-oriented use.

Approx. VRAM
High (large MoE)
License
Apache-2.0
Downloads
4.3M / 30d
#qwen#flash#moe#abliterated

updated Nov 10, 2026

Qwen27B
Abliteration

Qwen3.8-27B-Uncensored

Qwen/Qwen3.8-27B

Clean uncensored/abliterated Qwen 3.8 27B with multiple format options.

Approx. VRAM
~16.5 GB (Q4)
License
Apache-2.0
Downloads
2.2M / 30d
#qwen#uncensored#gguf

updated Nov 12, 2026

Qwen27B
Heretic-ARA

Qwen3.8-27B-Heretic-Abliterated-Uncensored

Qwen/Qwen3.8-27B

Heretic + ARA refined build. Frequently cited for very low refusal scores and low KL divergence.

Approx. VRAM
~16–17 GB
License
Apache-2.0
Downloads
1.1M / 30d
#qwen#heretic#ara#low-refusal

updated Nov 5, 2026

Gemma12B
Abliteration

Huihui-gemma-4-12B-it-abliterated

google/gemma-4-12b-it

Solid mid-size Gemma 4 abliterated variant from the most active publisher.

Approx. VRAM
~8 GB
License
Apache-2.0 / Gemma
Downloads
850K / 30d
#gemma#abliterated#12b
ollama run huihui_ai/gemma-4-abliterated:12b

updated Nov 11, 2026

Gemma31B
Heretic-ARA

gemma-4-31B-it-uncensored-heretic

google/gemma-4-31b-it

Larger Gemma 4 Heretic build with reported strong refusal reduction.

Approx. VRAM
~18–19 GB (Q4)
License
Apache-2.0
Downloads
720K / 30d
#gemma#31b#heretic#ara

updated Nov 7, 2026

GLMFlash
Fine-tune

GLM-5.3-Flash-Uncensored

THUDM/GLM-5.3-Flash

Popular uncensored GLM-5.3 Flash variant with FP8 and GGUF options.

Approx. VRAM
High
License
MIT
Downloads
615K / 30d
#glm#uncensored#flash

updated Oct 25, 2026

DeepSeekLarge MoE
Abliteration

Huihui-DeepSeek-V4-Flash-0731-abliterated

deepseek-ai/DeepSeek-V4-Flash

Abliterated DeepSeek V4 Flash variant. High capability but requires significant hardware.

Approx. VRAM
Very high
License
MIT
Downloads
365K / 30d
#deepseek#flash#moe#abliterated

updated Oct 28, 2026

Llama8B
Abliteration

Meta-Llama-3-8B-Instruct-abliterated-v3

meta-llama/Meta-Llama-3-8B-Instruct

Classic early Llama 3 abliterated model. Still useful on lower-end hardware.

Approx. VRAM
~5–6 GB
License
Llama 3
Downloads
320K / 30d
#llama#8b#classic#abliterated

updated Dec 1, 2024

Gemma27B
Abliteration

gemma-3-27b-it-abliterated

google/gemma-3-27b-it

Well-known earlier abliteration by mlabonne. Still widely referenced.

Approx. VRAM
~16 GB
License
Gemma
Downloads
180K / 30d
#gemma#classic#abliterated

updated Apr 1, 2025

Llama70B
Abliteration

Llama-3.3-70B-Instruct-abliterated

meta-llama/Llama-3.3-70B-Instruct

Large Llama 3.3 abliterated variant for high-end local setups.

Approx. VRAM
~40+ GB
License
Llama 3.3
Downloads
95K / 30d
#llama#70b#abliterated

updated Sep 20, 2026

VRAM figures are practical estimates for Q4-style quantization and a moderate context window. Actual usage depends on the quant, context length, KV cache and whether layers are offloaded. Download counts are approximate 30-day figures and change often. Always verify the model card and license before downloading. You are responsible for how you use a model.