LTX-2.3-uncensored-v1.4
Otheruncensored
from Lightricks/LTX-2.3
↓ 66.7K♥ 932 repos
Laguna-S-2.1-Uncensored
Laguna-S-2.1-Uncensored is a abliterated and uncensored variant of poolside/Laguna-S-2.1, published on Hugging Face by SC117. It is other licence. It is distributed across 10 repositories in GGUF, Transformers and GGUF (imatrix) formats, totalling 6.8K downloads.
Specification
- Model name
- Laguna-S-2.1-Uncensored
- Source repository
- SC117/Laguna-S-2.1-Uncensored
- Base model
- poolside/Laguna-S-2.1
- Publisher
- SC117
- Parameters
- Not determinable from name
- Hardware class
- Unknown
- Licence
- other
- Task
- Text generation
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF, Transformers, GGUF (imatrix)
- First indexed
- 26 Jul 2026
- Last updated
- 7 Aug 2026
Ablation technique
How Laguna-S-2.1-Uncensored 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
“Laguna S 2.1 is a poolside ~118B total / ~8B active per token Mixture-of-Experts model for agentic coding and long-horizon work. Architecture highlights: token-choice routing with softplus gates, 256 routed experts + 1 shared expert (top-10), GQA, 1:3 global/sliding-window attention (48 layers: 12 global + 36 local...”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download SC117/Laguna-S-2.1-Uncensored-APEX-GGUF --local-dir ./laguna-s-2.1-uncensored
llama-cli -m ./laguna-s-2.1-uncensored/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "SC117/Laguna-S-2.1-Uncensored"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve SC117/Laguna-S-2.1-Uncensored --trust-remote-codeDownloads and variants (9)
Every published repository of Laguna-S-2.1-Uncensored, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| SC117/Laguna-S-2.1-Uncensored-APEX-GGUF | GGUF | 3.3K |
| mradermacher/Laguna-S-2.1-Uncensored-i1-GGUF | GGUF (imatrix) | 2.2K |
| mradermacher/Laguna-S-2.1-Uncensored-GGUF | GGUF | 581 |
| jabbatheduck/Laguna-S-2.1-Uncensored-GGUF | GGUF | 368 |
| SC117/Laguna-S-2.1-Uncensoredsource | Transformers | 179 |
| Bizarrrr/Laguna-S-2.1-Uncensored | Transformers | 79 |
| Rootkit7/Laguna-S-2.1-uncensored-GGUF | GGUF | 67 |
| ressl/Laguna-S-2.1-Uncensored | Transformers | 38 |
| Rootkit7/Laguna-S-2.1-uncensored | Transformers | 31 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Laguna-S-2.1-Uncensored 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.
- Declared licence is other, but the terms that bind you are poolside/Laguna-S-2.1’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 Laguna-S-2.1-Uncensored is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with SC117, and does not independently verify publisher claims. See responsible use.