Fentible/gemma-3-4b-it-abliterated-IQ1_S-GGUF

💎 Gemma 3 1B Abliterated • Gemma 3 12B Abliterated • Gemma 3 27B Abliterated

This is an uncensored version of google/gemma-3-4b-it created with a new abliteration technique. See this article to know more about abliteration.

---

This model was converted to GGUF format from mlabonne/gemma-3-4b-it-abliterated using llama.cpp via the Fentible's GGUF-repo-suite.

GGUF Repo Suite is based on a refactored fork of ggml.ai's GGUF-my-repo space, updated for offline use with windows and support for lower IQ quants.

imatrix.dat generated using bartowski's calibration_datav3.txt

Refer to the original model card for more details on the model.

---

Use with llama.cpp

Install llama.cpp through brew (works on Mac and Linux)

brew install llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo Fentible/gemma-3-4b-it-abliterated-IQ1_S-GGUF --hf-file gemma-3-4b-it-abliterated-IQ1_S-imat.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo Fentible/gemma-3-4b-it-abliterated-IQ1_S-GGUF --hf-file gemma-3-4b-it-abliterated-IQ1_S-imat.gguf -c 2048

Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.

Step 1: Clone llama.cpp from GitHub.

git clone https://github.com/ggerganov/llama.cpp

Step 2: Move into the llama.cpp folder and build it with LLAMA_CURL=1 flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).

cd llama.cpp && LLAMA_CURL=1 make

Step 3: Run inference through the main binary.

./llama-cli --hf-repo Fentible/gemma-3-4b-it-abliterated-IQ1_S-GGUF --hf-file gemma-3-4b-it-abliterated-IQ1_S-imat.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo Fentible/gemma-3-4b-it-abliterated-IQ1_S-GGUF --hf-file gemma-3-4b-it-abliterated-IQ1_S-imat.gguf -c 2048