The current, most capable model that runs on a single GPU.

vision 1b 4b 12b 27b

2,959 16 hours ago

Readme

This is an uncensored version of google/gemma-3-release 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.

Note

This model requires Ollama 0.6 or later. Download Ollama

Model

Text

ollama run huihui_ai/gemma3-abliterated:1b

Multimodal (Vision)

4B parameter model (128k context window)

ollama run huihui_ai/gemma3-abliterated:4b

12B parameter model (128k context window)

ollama run huihui_ai/gemma3-abliterated:12b

27B parameter model (128k context window)

ollama run huihui_ai/gemma3-abliterated:27b

References

HuggingFace

Donation

If you like it, please click ‘like’ and follow us for more updates.
You can follow x.com/support_huihui to get the latest model information from huihui.ai.

Your donation helps us continue our further development and improvement, a cup of coffee can do it.
  • bitcoin:
  bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge