base_model: TrevorJS/gemma-4-12B-it-uncensored base_model_relation: quantized pipeline_tag: text-generation language:
- en license: apache-2.0 tags:
- abliteration
- uncensored
- gemma-4
- gguf
gemma-4-12B-it-uncensored (GGUF)
GGUF quantizations of TrevorJS/gemma-4-12B-it-uncensored.
Requires a llama.cpp build from 2026-06-04 or later (PR #24118, which added
Gemma4Unifiedconversion + inference support). Earlier builds will fail to load these files.
Files
| File | Quant | Size |
|---|---|---|
gemma-4-12B-it-uncensored-Q4_K_M.gguf | Q4_K_M | 7.4 GB |
gemma-4-12B-it-uncensored-Q8_0.gguf | Q8_0 | 12.7 GB |
Usage
# From HuggingFace (auto-downloads)
llama-server -hf TrevorJS/gemma-4-12B-it-uncensored-GGUF -c 8192
# From local file
llama-server -m gemma-4-12B-it-uncensored-Q4_K_M.gguf -c 8192
Then open http://localhost:8080 for the chat UI.
Details
These are GGUF quantizations of TrevorJS/gemma-4-12B-it-uncensored, an abliterated (uncensored) version of google/gemma-4-12B-it. Refusal behavior has been removed using norm-preserving biprojected abliteration.
See the bf16 model card for full method details, before/after refusal rates, and cross-dataset validation results.
Source code: TrevorJS/gemma-4-abliteration