LFM2.5-2.6B-Uncensored
2.6BOtheruncensored
from LiquidAI/LFM2.5-2.6B
↓ 17.3K♥ 178 repos
LFM2.5-2.6B-Heretic-Abliterated
LFM2.5-2.6B-Heretic-Abliterated is a Heretic-ablated variant of LiquidAI/LFM2.5-2.6B, published on Hugging Face by Abiray. It is 2.6B parameters, runs on a laptop CPU class and apache-2.0 licence. It is distributed across 3 repositories in GGUF format, totalling 16.6K downloads.
Specification
- Model name
- LFM2.5-2.6B-Heretic-Abliterated
- Source repository
- Abiray/LFM2.5-2.6B-Heretic-Abliterated-GGUF
- Base model
- LiquidAI/LFM2.5-2.6B
- Publisher
- Abiray
- Parameters
- 2.6B
- Hardware class
- Under 4B — runs on a laptop CPU
- Licence
- apache-2.0
- Task
- Text generation
- Context window
- 128K tokens (as documented)
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF
- First indexed
- 5 Aug 2026
- Last updated
- 6 Aug 2026
Ablation technique
How LFM2.5-2.6B-Heretic-Abliterated 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
“This repository contains GGUF quantizations of the LFM2.5-2.6B-Heretic model.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download Abiray/LFM2.5-2.6B-Heretic-Abliterated-GGUF --local-dir ./lfm2.5-2.6b-heretic-abliterated
llama-cli -m ./lfm2.5-2.6b-heretic-abliterated/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "Abiray/LFM2.5-2.6B-Heretic-Abliterated-GGUF"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve Abiray/LFM2.5-2.6B-Heretic-Abliterated-GGUF --trust-remote-codeDownloads and variants (2)
Every published repository of LFM2.5-2.6B-Heretic-Abliterated, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| Abiray/LFM2.5-2.6B-Heretic-Abliterated-GGUFsource | GGUF | 16.3K |
| nguyenthilaitrieulong/LFM2.5-2.6B-Heretic-Abliterated-GGUF | GGUF | 312 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- LFM2.5-2.6B-Heretic-Abliterated 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 LiquidAI/LFM2.5-2.6B, not added by ablation — at 2.6B 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 LiquidAI/LFM2.5-2.6B’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 LFM2.5-2.6B-Heretic-Abliterated is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with Abiray, and does not independently verify publisher claims. See responsible use.