Gemma-4-E2B-Uncensored is an open-weight model from SkillSafe AI. Its published files total 2.0 GB.
A variant of Google's Gemma 4 E2B-it fine-tuned model, quantized for the LiteRT-LM browser runtime (int4/int2 weights, int8 static activation quantization).
Model Card
A variant of Google's Gemma 4 E2B-it fine-tuned model, quantized for the LiteRT-LM browser runtime (int4/int2 weights, int8 static activation quantization). The abliteration edit from the GGUF model was reverse-engineered as a rank-1 direction per matrix layer. About 35% of the edit survives quantization to Google's int4/int2 grid with per-channel scales (mostly in attention output and FFN matrices; less in int2 layers). The result is a model with substantially weakened or removed refusals while maintaining similar generation quality. The model has minimal resistance to requests regardless of framing or content type. It is not suitable for applications requiring strong safety guardrails.…
Excerpt from the card by SkillSafe AI.
Identity and Version
- Repository
- skillsafe-ai/Gemma-4-E2B-Uncensored
- Publisher
- SkillSafe AI
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- f3f7dc7ea246bcd8a6f328539197fe82f4c50487
- First published
- 2026-10-02
- Last updated
- 2026-10-02
Files and Weights
3 files, 2.0 GB in total.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| README.md | Documentation | 2.1 KB | — |
| model.litertlm | Other | 2.0 GB | a6132d4e449c |
| .gitattributes | Repository | 1.6 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
Released by SkillSafe AI through its official repository on Hugging Face.