Uncensored LLMs
227 uncensored language models, most downloaded first: the model each is based on, how its limits were removed, and where to get it.
AIModelFind lists these models from public sources; it does not host or run them. Check each model's license and the law where you use it.
| Model | Based on | Method | Download as | Downloads / mo | Hosted API |
|---|---|---|---|---|---|
Dolphin 2.9.1 Yi 1.5 34B by dphn | 01-ai/Yi-1.5-34B | Fine-tuned | safetensors | 4.5M | Weights only |
 Huihui-Qwen3.8-27B-abliterated by huihui-ai | Qwen3.8 27B | Abliterated | GGUF · safetensors | 2.5M | Weights only |
J Qwen3.8-27B-Uncensored by JonathanColetti | Qwen3.8 27B | Abliterated | AWQ · GGUF · safetensors | 2.5M | Weights only |
H | Qwen3.8 27B | Fine-tuned | GGUF | 2.3M | Weights only |
| Qwen3.8 Flash Next | Abliterated | GGUF | 2.2M | Weights only | |
| Qwen3.5 9B | Abliterated | GGUF | 1.8M | Weights only | |
| Qwen3.8 27B | Abliterated | GGUF · safetensors | 1.7M | Weights only | |
H | Qwen3.6 35B-A3B | Fine-tuned | GGUF · safetensors | 1.5M | Weights only |
0 Qwen3.8-27B-Heretic-Abliterated-Uncensored by 0bserverx | Qwen3.8 27B | Abliterated | GGUF | 1.1M | Weights only |
 Qwen3.8-Flash-Next-Uncensored by orcarouter | Qwen3.8 Flash Next | Fine-tuned | FP8 · GGUF | 1M | Weights only |
H Gemma-4-E4B-Uncensored-HauhauCS-Aggressive by HauhauCS | — | Fine-tuned | safetensors | 920K | Weights only |
H Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced by HauhauCS | Gemma 4 12B Instruct | Fine-tuned | safetensors | 832K | Weights only |
p Qwen3.8-27B-Uncensored-Cyber by philbert440 | Qwen3.8 27B | Fine-tuned | GGUF | 800K | Weights only |
GLM-5.3-Flash-Uncensored by orcarouter | GLM-5.3-Flash | Fine-tuned | FP8 · GGUF | 615K | $0.80/1M NanoGPT |
Qwen3.8-27B-Uncensored by orcarouter | Qwen3.8 27B | Fine-tuned | FP8 · GGUF · MLX · safetensors | 615K | Weights only |
| Qwen3.6 27B | Abliterated | GGUF | 449K | Weights only | |
B Qwen3.6-35B-A3B-abliterated-v4 by Bahushruth | Qwen3.6 35B-A3B | Abliterated | safetensors | 447K | Weights only |
| Gemma 4 26B A4B IT | Fine-tuned | safetensors | 382K | Weights only | |
Huihui-Qwen3.8-Flash-Next-abliterated by huihui-ai | Qwen3.8 Flash Next | Abliterated | GGUF | 379K | Weights only |
0 RVN-Qwen3.8-Flash-Next-Abliterated-Uncensored by 0bserverx | Qwen3.8 Flash Next | Abliterated | GGUF · safetensors | 374K | Weights only |
j Swift-1.5-Qwen3.8-27B-heretic-GSQ-RCO by jegreene | Qwen3.8 27B | Abliterated | GGUF | 359K | Weights only |
Huihui-DeepSeek-V4-Flash-0731-abliterated by huihui-ai | DeepSeek V4 Flash 0731 | Abliterated | GGUF | 324K | Weights only |
Qwen2.5-VL-7B-Instruct-abliterated by huihui-ai | Qwen/Qwen2.5-VL-7B-Instruct | Abliterated | safetensors | 280K | Weights only |
D | Qwen3 8B | Fine-tuned | safetensors | 265K | Weights only |
 Ornith-1.5-9B-UNCENSORED by dealignai | ornith-ai/Ornith-1.5-9B | Fine-tuned | GGUF | 248K | Weights only |
| Qwen3.8 Flash Next | Abliterated | GGUF | 247K | Weights only | |
a Qwen3.8-Flash-Next-abliterated-GSQ-RCO-Strata by alesha-pro | Qwen3.8 Flash Next | Abliterated | GGUF | 224K | Weights only |
Huihui-Qwen3.6-35B-A3B-abliterated-MTP by huihui-ai | Qwen3.6 35B-A3B | Abliterated | GGUF | 199K | Weights only |
O Ternary-Bonsai-2-27B-Uncensored-Heretic by OS-Software | prism-ml/Ternary-Bonsai-2-27B-gguf | Abliterated | GGUF | 197K | Weights only |
s Spark-X2.5-4B-Heretic-jp by soyaakinohara | XHToken/Spark-X2.5-4B | Abliterated | GGUF | 176K | Weights only |
f Meta-Llama-3-8B-Instruct-abliterated-v3 by failspy | — | Abliterated | safetensors | 164K | Weights only |
| llmfan46/gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic | Abliterated | GGUF | 161K | Weights only | |
H | Qwen3.5 122B-A10B | Fine-tuned | safetensors | 143K | Weights only |
a Qwen3.8-27B-Uncensored by azukivc | Qwen3.8 27B | Fine-tuned | GGUF | 137K | Weights only |
DeepSeek-V4.1-Flash-UNCENSORED by dealignai | DeepSeek V4 Flash Vision Exp | Fine-tuned | FP8 | 129K | $1.32/1M Venice AI |
| Qwen3.6 35B-A3B | Abliterated | GGUF · GPTQ | 128K | Weights only | |
Huihui-Qwen3.8-Flash-Next-abliterated-v2 by huihui-ai | Qwen3.8 Flash Next | Abliterated | GGUF | 112K | Weights only |
a Swift-1.5-Qwen3.8-27B-Uncensored-MTP by ajgazin | Qwen3.8 27B | Fine-tuned | GGUF | 111K | Weights only |
t Qwen3.6-35B-A3B-heretic by tvall43 | Qwen3.6 35B-A3B | Abliterated | — | 101K | Weights only |
| Qwen3.6 27B | Fine-tuned | safetensors | 100K | Weights only | |
| empero-ai/Qwen3.8-35B-A3B-Distill | Abliterated | GGUF | 96K | Weights only | |
c Gemma 4 12B Heretic Abliterated by culturerevolt | culturerevolt/gemma-4-12b-heretic-abliterated | Abliterated | GGUF | 96K | Weights only |
z Gemma 4 12B It Uncensored by zaakirio | Gemma 4 12B Instruct | Fine-tuned | GGUF | 93K | Weights only |
H | Qwen3.5 35B-A3B | Fine-tuned | safetensors | 88K | Weights only |
H Gemma-4-E2B-Uncensored-HauhauCS-Aggressive by HauhauCS | — | Fine-tuned | safetensors | 86K | Weights only |
H | Gemma 4 | Fine-tuned | safetensors | 84K | Weights only |
l gemma-4-E4B-it-ultra-uncensored-heretic by llmfan46 | llmfan46/gemma-4-E4B-it-ultra-uncensored-heretic | Abliterated | GGUF | 81K | Weights only |
Huihui-Qwen3.5-27B-abliterated by huihui-ai | Qwen3.5 27B | Abliterated | safetensors | 81K | Weights only |
l gemma-4-31B-it-uncensored-heretic by llmfan46 | Gemma 4 | Abliterated | GGUF | 80K | Weights only |
H Gemma4-26B-A4B-Uncensored-HauhauCS-Balanced by HauhauCS | Gemma 4 26B A4B IT | Fine-tuned | safetensors | 78K | Weights only |
Frequently asked questions
A model with the refusals and content filters of the original taken out: by removing the refusal direction from its weights (abliteration), by fine-tuning on unfiltered data, or by merging models. What it knows stays the same; what it agrees to answer changes.
No. AIModelFind collects public information only: who released each model, what it is based on, where its weights are and which providers host it. The downloads and APIs belong to their authors and providers.
Most come as GGUF or MLX files, which run locally in tools such as llama.cpp, Ollama or LM Studio. Pick a quantization that fits your memory; the larger the file, the closer it stays to the full model.
Can't find what you're looking for? Contact us