gemma-4-E2B-it-uncensored
Gemmauncensored
from google/gemma-4-E2B-it
↓ 43.2K♥ 6629 repos
gemma-4-E2B-it-heretic
gemma-4-E2B-it-heretic is a Heretic-ablated variant of google/gemma-4-E2B-it, published on Hugging Face by p-e-w. It is apache-2.0 licence. It is distributed across 15 repositories in Transformers, GGUF, GGUF (imatrix) and MLX formats, totalling 6.4K downloads.
Specification
- Model name
- gemma-4-E2B-it-heretic
- Source repository
- p-e-w/gemma-4-E2B-it-heretic
- Base model
- google/gemma-4-E2B-it
- Publisher
- p-e-w
- Parameters
- Not determinable from name
- VRAM required
- Unknown — no published parameter count
- Hardware class
- Unknown
- Licence
- apache-2.0
- Task
- Any to any
- Context window
- 128K tokens (as documented)
- Ablation scope
- Not stated by the publisher
- Formats available
- Transformers, GGUF, GGUF (imatrix), MLX
- First indexed
- 3 Apr 2026
- Last updated
- 1 Nov 2026
Ablation technique
How gemma-4-E2B-it-heretic was modified, and what that implies.
Heretic
Automated directional ablation via the Heretic toolchain, which searches for the refusal direction and applies it with a KL-divergence budget so general capability is preserved.
Reported scope: Not stated by the publisher. Publishers frequently omit this, so verify behaviour empirically rather than assuming full coverage.
From the publisher’s model card
“Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on small models) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants. Gemma 4 features a context window of...”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download saidutta69/gemma-4-E2B-it-heretic --local-dir ./gemma-4-e2b-it-heretic
llama-cli -m ./gemma-4-e2b-it-heretic/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "p-e-w/gemma-4-E2B-it-heretic"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve p-e-w/gemma-4-E2B-it-heretic --trust-remote-codeDownloads and variants (14)
Every published repository of gemma-4-E2B-it-heretic, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| saidutta69/gemma-4-E2B-it-heretic | GGUF | 2.8K |
| mradermacher/gemma-4-E2B-it-heretic-GGUF | GGUF | 1.4K |
| JMingo/gemma-4-E2B-it-heretic-UD-GGUF | GGUF | 442 |
| mradermacher/gemma-4-E2B-it-heretic-i1-GGUF | GGUF (imatrix) | 411 |
| Stabhappy/gemma-4-E2B-it-heretic-GGUF | GGUF | 281 |
| atakankutalp/gemma-4-E2B-it-heretic | GGUF | 278 |
| FadedRedStar/gemma-4-E2B-it-heretic-GGUF | GGUF | 262 |
| gabrielmtzcarrillo/gemma-4-E2B-it-heretic-gguf | GGUF | 207 |
| FadedRedStar/gemma-4-E2B-it-heretic-imatrix-GGUF | GGUF | 182 |
| p-e-w/gemma-4-E2B-it-hereticsource | Transformers | 48 |
| coder3101/gemma-4-E2B-it-heretic | Transformers | 47 |
| MoonRide/gemma-4-E2B-it-heretic | Transformers | 8 |
| FeverK/gemma-4-E2B-it-heretic | Transformers | 6 |
| atakankutalp/gemma-4-E2B-it-MLX-heretic | MLX | 0 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- gemma-4-E2B-it-heretic will attempt offensive-security prompts that a hosted commercial model declines, which is what makes it usable for red-team corpus generation and for measuring what an unaligned model of this class produces.
- The publisher does not state which layers were ablated, so assume nothing about refusal consistency — probe it directly.
- Declared licence is apache-2.0, but the terms that bind you are google/gemma-4-E2B-it’s — a re-release cannot grant more than its parent.
Handling: run it isolated, put moderation in front of it if anyone outside your team can reach it, and verify the weights before loading — these are third-party artifacts. Full handling and licence guidance.
Metadata for gemma-4-E2B-it-heretic is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with p-e-w, and does not independently verify publisher claims. See responsible use.