LFM3-1.7B-Uncensored
1.7BOtheruncensored
from LiquidAI/LFM3-1.7B
↓ 85.8K♥ 2475 repos
K2-Horizon-3.7B-heretic-xortron
K2-Horizon-3.7B-heretic-xortron is a Heretic-ablated variant of darkc0de/K2-Horizon-3.7B-heretic-xortron, published on Hugging Face by darkc0de. It is 3.7B parameters, runs on a laptop CPU class and apache-2.0 licence. It is distributed across 5 repositories in Transformers, GGUF and GGUF (imatrix) formats, totalling 6.4K downloads.
Specification
- Model name
- K2-Horizon-3.7B-heretic-xortron
- Source repository
- darkc0de/K2-Horizon-3.7B-heretic-xortron
- Base model
- darkc0de/K2-Horizon-3.7B-heretic-xortron
- Publisher
- darkc0de
- Parameters
- 3.7B
- VRAM required
- ~3 GB at Q4_K_M, 4k context (estimated) — runs on 4 GB cards
- Hardware class
- Under 4B — runs on a laptop CPU
- Licence
- apache-2.0
- Task
- Text generation
- Context window
- 512K tokens (as documented)
- Ablation scope
- Not stated by the publisher
- Formats available
- Transformers, GGUF, GGUF (imatrix)
- First indexed
- 15 Sept 2026
- Last updated
- 14 Oct 2026
Ablation technique
How K2-Horizon-3.7B-heretic-xortron 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
“K2-Horizon-3.7B is the small dense member of the K2-Horizon family: a 3.7B-core decoder-only model with a 512K context window.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download mradermacher/K2-Horizon-3.7B-heretic-xortron-i1-GGUF --local-dir ./k2-horizon-3.7b-heretic-xortron
llama-cli -m ./k2-horizon-3.7b-heretic-xortron/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "darkc0de/K2-Horizon-3.7B-heretic-xortron"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve darkc0de/K2-Horizon-3.7B-heretic-xortron --trust-remote-codeDownloads and variants (4)
Every published repository of K2-Horizon-3.7B-heretic-xortron, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| mradermacher/K2-Horizon-3.7B-heretic-xortron-i1-GGUF | GGUF (imatrix) | 4.8K |
| mradermacher/K2-Horizon-3.7B-heretic-xortron-GGUF | GGUF | 1.4K |
| darkc0de/K2-Horizon-3.7B-heretic-xortronsource | Transformers | 288 |
| Cdsnutz/K2-Horizon-3.7B-heretic-xortron | Transformers | 37 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- K2-Horizon-3.7B-heretic-xortron 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.
- Capability is inherited from darkc0de/K2-Horizon-3.7B-heretic-xortron, not added by ablation — at 3.7B parameters, expect a small model’s reasoning and a high error rate on exploit detail.
- 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 darkc0de/K2-Horizon-3.7B-heretic-xortron’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 K2-Horizon-3.7B-heretic-xortron is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with darkc0de, and does not independently verify publisher claims. See responsible use.