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 |
|---|---|---|---|---|---|
| DavidAU/Gemma-3-4B-VL-it-Gemini-Pro-Heretic-Uncensored-Thinking | Abliterated | GGUF | 13K | Weights only | |
Dolphin3.0-Llama3.2-3B by dphn | dphn/Dolphin3.0-Llama3.2-3B | Fine-tuned | GGUF | 13K | Weights only |
F Qwen3.8-9B-heretic-uncensored-4bit-MTPLX by Foresee | — | Abliterated | safetensors | 12K | Weights only |
x | Qwen3.8 27B | Abliterated | GGUF | 12K | Weights only |
Dolphin3.0-Qwen2.5-3b by dphn | dphn/Dolphin3.0-Qwen2.5-3b | Fine-tuned | GGUF | 12K | Weights only |
d Dongfangshuo-Qwen3.8-Flash-Next-NSFW by dongfangshuo | Qwen3.8 Flash Next | Fine-tuned | safetensors | 12K | Weights only |
U NSFW-flash by UnfilteredAI | — | Fine-tuned | safetensors | 12K | Weights only |
t Qwen3.8-27B-heretic-ara by trohrbaugh | Qwen3.8 27B | Abliterated | GGUF | 11K | Weights only |
| DavidAU/Qwen3.6-12B-IQ-Ultra-Heretic-Uncensored-Thinking-V2-Hightop | Abliterated | GGUF | 11K | Weights only | |
c gemma-4-E4B-it-heretic by coder3101 | coder3101/gemma-4-E4B-it-heretic | Abliterated | GGUF | 11K | Weights only |
Dolphin3.0-R1-Mistral-24B by dphn | dphn/Dolphin3.0-R1-Mistral-24B | Fine-tuned | GGUF | 11K | Weights only |
Dolphin 2.8 Mistral 7B V02 by dphn | Mistral 7B Instruct | Fine-tuned | GGUF · safetensors | 10K | Weights only |
D Gemma 3 12B It Heretic V2 by DreamFast | Gemma 3 12B IT | Abliterated | safetensors | 10K | Weights only |
b thesby_Qwen2.5-VL-7B-NSFW-Caption-V3 by bartowski | — | Fine-tuned | GGUF | 10K | Weights only |
Dolphin 2.9.1 Mixtral 1x22b by dphn | mistral-community/Mixtral-8x22B-v0.1 | Fine-tuned | safetensors | 10K | Weights only |
A MiniCPM-V-4.7-1B-abliterated-heretic by Abiray | openbmb/MiniCPM-V-4.7-1B | Abliterated | GGUF | 10K | Weights only |
| Mistral Nemo | Abliterated | safetensors | 10K | Weights only | |
c Qwen3.5-4B-heretic by coder3101 | Qwen3.5 4B | Abliterated | GGUF | 10K | Weights only |
Dolphin3.0-Qwen2.5-1.5B by dphn | dphn/Dolphin3.0-Qwen2.5-1.5B | Fine-tuned | GGUF | 9K | Weights only |
b dolphin-2.9.3-Yi-1.5-34B-32k by bartowski | — | Fine-tuned | GGUF | 9K | Weights only |
Dolphin 2.9.1 Llama 3 70B by dphn | Llama 3 70B Instruct | Fine-tuned | safetensors | 9K | Weights only |
Dolphin 2.9.2 Mixtral 8x22b by dphn | Mixtral 8x22B Instruct | Fine-tuned | safetensors | 8K | Weights only |
Dolphin 2.9.1 Yi 1.5 9B by dphn | 01-ai/Yi-1.5-9B | Fine-tuned | safetensors | 8K | Weights only |
Dolphin 2.6 Mixtral 8x7b by dphn | Mixtral 8x7b Instruct | Fine-tuned | safetensors | 8K | Weights only |
dolphin-2.9.3-Yi-1.5-34B-32k by dphn | — | Fine-tuned | safetensors | 8K | Weights only |
| unsloth/Phi-3-mini-4k-instruct | Abliterated | safetensors | 8K | Weights only | |
s NSFW-Panda-7B by s3nh | — | Fine-tuned | GGUF | 7K | Weights only |
Dolphin 2.9.4 Llama3.1 8B by dphn | dphn/dolphin-2.9.4-llama3.1-8b | Fine-tuned | GGUF | 6K | Weights only |
Dolphin3.0-Llama3.2-1B by dphn | dphn/Dolphin3.0-Llama3.2-1B | Fine-tuned | GGUF | 6K | Weights only |
Dolphin 2.8 Mistral 7B V02 by lmstudio-community | Mistral 7B Instruct | Fine-tuned | GGUF | 6K | Weights only |
Dolphin 2.9.2 Qwen2 7B by dphn | Qwen2-7B-Instruct | Fine-tuned | GGUF | 6K | Weights only |
b Dolphin 2.9.1 Mixtral 1x22b by bartowski | mistral-community/Mixtral-8x22B-v0.1 | Fine-tuned | GGUF | 5K | Weights only |
 GLM-4.6-Derestricted-v3 by ArliAI | GLM-4.6 | Fine-tuned | GGUF · safetensors | 4K | Weights only |
m Meta-Llama-3.1-8B-Instruct-abliterated by mlabonne | Llama 3.1 8B Instruct | Fine-tuned | safetensors | 4K | Weights only |
P | SulphurAI/Sulphur-2-base | Fine-tuned | GGUF | 4K | Weights only |
Dolphin-X1-8B by dphn | dphn/Dolphin-X1-8B | Fine-tuned | GGUF | 3K | Weights only |
M Dirty-Muse-Writer-v01-Uncensored-Erotica-NSFW by Mantis2024 | Mantis2024/Dirty-Muse-Writer-v01-Uncensored-Erotica-NSFW | Merged | MLX | 3K | Weights only |
M NSFW_DPO_Noromaid-7b-Mistral-7B-Instruct-v0.1 by MaziyarPanahi | Mistral-7B-Instruct-v0.1 | Merged | GGUF | 3K | Weights only |
z NSFW_13B_sft by zxbsmk | zxbsmk/NSFW_13B_sft | Fine-tuned | GGUF | 3K | Weights only |
b dolphin-2.9.3-mistral-7B-32k by bartowski | Mistral 7B Instruct | Fine-tuned | GGUF | 3K | Weights only |
GLM-4.5-Air-Derestricted by ArliAI | GLM-4.5-Air | Fine-tuned | GGUF | 3K | Weights only |
b Dolphin 2.9.1 Llama 3 70B by bartowski | Llama 3 70B Instruct | Fine-tuned | GGUF | 3K | Weights only |
| uukuguy/speechless-mistral-dolphin-orca-platypus-samantha-7b | Fine-tuned | GGUF | 3K | Weights only | |
| mistralai/Mistral-Nemo-Base-2407 | Fine-tuned | safetensors | 3K | Weights only | |
Dolphin-X1-Trinity-Nano by dphn | arcee-ai/Trinity-Nano-Preview | Fine-tuned | GGUF | 2K | Weights only |
K | GLM-4.5-Air | Fine-tuned | safetensors | 2K | Weights only |
S Dolphin3-Cyber-8B by ScottzillaSystems | — | Fine-tuned | GGUF | 2K | Weights only |
Dolphin3.0-Qwen2.5-0.5B by dphn | dphn/Dolphin3.0-Qwen2.5-0.5B | Fine-tuned | GGUF | 2K | Weights only |
m Dolphin3-Cyber-8B by meowmeow123ok | — | Fine-tuned | GGUF | 2K | Weights only |
p FLUX 3 Image Klein Prompt Upsampler Abliterated by prithivMLmods | prithivMLmods/flux-3-image-klein-prompt-upsampler-abliterated | Abliterated | GGUF | 2K | 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