LFM2.5-2.6B-Uncensored
2.6BOtheruncensored
from LiquidAI/LFM2.5-2.6B
↓ 17.3K♥ 178 repos
LFM2.5-VL-3B-absolute-heresy
LFM2.5-VL-3B-absolute-heresy is a Heretic-ablated variant of MuXodious/LFM2.5-VL-3B-absolute-heresy, published on Hugging Face by MuXodious. It is 3B parameters, runs on a laptop CPU class and other licence. It is distributed across 4 repositories in Transformers, GGUF and GGUF (imatrix) formats, totalling 6.4K downloads.
Specification
- Model name
- LFM2.5-VL-3B-absolute-heresy
- Source repository
- MuXodious/LFM2.5-VL-3B-absolute-heresy
- Base model
- MuXodious/LFM2.5-VL-3B-absolute-heresy
- Publisher
- MuXodious
- Parameters
- 3B
- Hardware class
- Under 4B — runs on a laptop CPU
- Licence
- other
- Task
- Image text to text
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- Transformers, GGUF, GGUF (imatrix)
- First indexed
- 12 Aug 2026
- Last updated
- 13 Aug 2026
Ablation technique
How LFM2.5-VL-3B-absolute-heresy 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 is an LFM2.5-VL-3B fine-tune, produced through P-E-W's Heretic (v1.4.0) abliteration engine with Self-Organizing Maps & Magnitude-Preserving Orthogonal Ablation enabled.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download mradermacher/LFM2.5-VL-3B-absolute-heresy-i1-GGUF --local-dir ./lfm2.5-vl-3b-absolute-heresy
llama-cli -m ./lfm2.5-vl-3b-absolute-heresy/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "MuXodious/LFM2.5-VL-3B-absolute-heresy"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve MuXodious/LFM2.5-VL-3B-absolute-heresy --trust-remote-codeDownloads and variants (3)
Every published repository of LFM2.5-VL-3B-absolute-heresy, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| mradermacher/LFM2.5-VL-3B-absolute-heresy-i1-GGUF | GGUF (imatrix) | 4.7K |
| mradermacher/LFM2.5-VL-3B-absolute-heresy-GGUF | GGUF | 1.6K |
| MuXodious/LFM2.5-VL-3B-absolute-heresysource | Transformers | 100 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- LFM2.5-VL-3B-absolute-heresy 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 MuXodious/LFM2.5-VL-3B-absolute-heresy, not added by ablation — at 3B 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 other, but the terms that bind you are MuXodious/LFM2.5-VL-3B-absolute-heresy’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-VL-3B-absolute-heresy is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with MuXodious, and does not independently verify publisher claims. See responsible use.