license: apache-2.0 base_model:

• google/gemma-4-E4B-it
• litert-community/gemma-4-E4B-it-litert-lm library_name: litert-lm pipeline_tag: text-generation tags:
• litert-lm
• gemma
• gemma-4
• abliterated
• uncensored
• on-device
• android
• mtp extra_gated_prompt: >- This is an ABLITERATED model: its trained refusal behavior has been removed and it will attempt to answer harmful or unsafe requests. It is released for research and personal experimentation only. By requesting access you confirm you are using it responsibly and accept sole responsibility for any outputs and downstream use. extra_gated_fields: I use this for research / personal experimentation only: checkbox I accept responsibility for the outputs and any downstream use: checkbox

Gemma 4 E4B - abliterated, on-device (.litertlm)

An abliterated (refusal-removed) build of Gemma 4 E4B, packaged as a single .litertlm for the LiteRT-LM runtime: mobile wNa8o8 quantization (mixed int4/int8 weights + static int8 activations), Multi-Token Prediction (MTP) speculative decoding, and the multimodal encoders - all intact. Runs on Android / desktop / iOS via CPU (XNNPACK) or GPU (ML Drift).

Safety. Refusals are removed. This model will comply with harmful requests. Research / personal use only - you own the outputs.

How it was made (novel bit)

Rather than rebuilding a .litertlm from scratch (public tooling can't reproduce Gemma 4's MTP wiring), the working litert-community/gemma-4-E4B-it-litert-lm artifact was patched in place: only the o_proj/down_proj weights inside the quantized prefill_decode.tflite were edited, so the embedder, tokenizer and MTP drafter survive byte-for-byte.

Because a norm-preserving biprojected abliteration edit is smaller than the int4 quantization step, plain round-to-nearest requant erases it. A directional error-feedback requantizer preserves the refusal-direction removal on the int4 grid. Full method + code: repo.

Quality & behavior (measured)

• Refusal removed: on prompts the stock model hard-refuses ("I cannot provide instructions…"), this model complies.
• Quality cost: activation-weighted requant error ≈ 71% of the int4 rounding floor Google already ships - i.e. within the quantization-noise envelope the QAT model tolerates. ~2.5% of o_proj/down_proj int4 codes changed.
• MTP lossless: greedy output is identical with speculative decoding on/off.

This is unbenchmarked territory (QAT + abliteration + int4 requant); no perplexity / standardized refusal-rate benchmark has been run. Treat quality claims as directional.

Run it

uv tool install litert-lm
litert-lm run gemma-4-E4B-it-abliterated.litertlm \
  --backend=gpu --enable-speculative-decoding=true \
  --prompt="…"

Or use the minimal Android app in the repo.

Limitations & risks

• No safety guardrails. May produce harmful, biased, or false content.
• Abliteration can slightly degrade instruction-following on some prompts and may show "refuse-then-comply" on a few.
• int4 + abliteration is a small perturbation on top of Google's mobile quant; quality is close to the stock .litertlm but not identical.

Attribution

Base: Google Gemma 4 E4B + LiteRT-LM + litert-community .litertlm (all Apache-2.0). Method: biprojection (grimjim) / p-e-w/heretic; Gemma-4 recipe from TrevorS/gemma-4-abliteration. The int4 in-place patch is original. Base Gemma 4 Prohibited Use Policy applies. Licensed Apache-2.0; modifications = abliteration + int4 requant.