
Base	google/gemma-4-E4B-it (4.5B)
Source	OBLITERATUS/gemma-4-E4B-it-OBLITERATED — 0% hard refusal (vs 98.8% stock)
Quant	4-bit MLX \| 3.9 GB disk \| ~4.3 GB RAM
Speed	73.8 tok/s generation on M4 Pro
License	Apache 2.0

Quick Start

bash

pip install mlx-lm

# CLI
mlx_lm generate --model zaydiscold/gemma-4-E4B-it-OBLITERATED-MLX-4bit \
    --prompt "Your prompt here"

python

from mlx_lm import load, generate
model, tokenizer = load("zaydiscold/gemma-4-E4B-it-OBLITERATED-MLX-4bit")
response = generate(model, tokenizer, prompt="Your prompt here", max_tokens=512)

Recommended: temperature=0.7, top_p=0.9, top_k=40, repeat_penalty=1.1

OBLITERATUS

OBLITERATUS by @elder_plinius removes refusal behavior via whitened SVD, attention head surgery (21/42 layers), winsorized activations, and SVD projection on refusal subspaces. Full methodology on the source model card.

Credits

OBLITERATUS / @elder_plinius -- abliteration | Google DeepMind -- Gemma 4 | @zaydiscold -- MLX 4-bit | Apple MLX

Research/red-teaming only. You are responsible for all generated content. Full terms.