LTX-2.3-uncensored-v1.4
Otheruncensored
from Lightricks/LTX-2.3
↓ 66.7K♥ 932 repos
UNSEEN_Gemma_4_26B_NSFW
UNSEEN_Gemma_4_26B_NSFW is a abliterated and uncensored open-weight language model, published on Hugging Face by Jommarn. It is distributed across 4 repositories in GGUF and Transformers formats, totalling 22K downloads.
Specification
- Model name
- UNSEEN_Gemma_4_26B_NSFW
- Source repository
- Jommarn/UNSEEN_Gemma_4_26B_NSFW
- Base model
- Not declared
- Publisher
- Jommarn
- Parameters
- Not determinable from name
- Hardware class
- Unknown
- Licence
- Not declared
- Task
- Image text to text
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF, Transformers
- First indexed
- 19 Aug 2026
- Last updated
- 2 Sept 2026
Ablation technique
How UNSEEN_Gemma_4_26B_NSFW was modified, and what that implies.
Abliteration + uncensored fine-tune
Directional ablation combined with additional fine-tuning on unfiltered data, so behaviour diverges from the base model beyond refusal removal alone.
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
“This model is a permanently abliterated (uncensored) version of google/gemma-4-26B-A4B-it. The refusal mechanisms have been surgically removed from the model's weights using Orthogonal Weight Projection (Abliteration) across all transformer layers (oproj and downproj).”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download Jommarn/UNSEEN_Gemma_4_26B_NSFW-GGUF --local-dir ./unseen-gemma-4-26b-nsfw
llama-cli -m ./unseen-gemma-4-26b-nsfw/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "Jommarn/UNSEEN_Gemma_4_26B_NSFW"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve Jommarn/UNSEEN_Gemma_4_26B_NSFW --trust-remote-codeDownloads and variants (3)
Every published repository of UNSEEN_Gemma_4_26B_NSFW, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| Jommarn/UNSEEN_Gemma_4_26B_NSFW-GGUF | GGUF | 19.4K |
| Jommarn/UNSEEN_Gemma_4_26B_NSFWsource | Transformers | 1.9K |
| Jommarn-Ai/UNSEEN_Gemma_4_26B_NSFW-IQ2_M-GGUF | GGUF | 701 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- UNSEEN_Gemma_4_26B_NSFW 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.
- This release adds fine-tuning on unfiltered data, so its behaviour diverges from the base model beyond refusal removal — differences you measure cannot be attributed to ablation alone.
- No licence is declared on this repository, which is a compliance problem in itself. Resolve it against the base model’s terms before use.
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 UNSEEN_Gemma_4_26B_NSFW is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with Jommarn, and does not independently verify publisher claims. See responsible use.