LFM3-1.7B-Uncensored
1.7BOtheruncensored
from LiquidAI/LFM3-1.7B
↓ 85.8K♥ 2475 repos
lfm3-vl-2b-heretic
lfm3-vl-2b-heretic is a Heretic-ablated variant of LiquidAI/LFM3-VL-2B, published on Hugging Face by Lucasgitguy-co. It is 2B parameters, runs on a laptop CPU class and other licence. It is distributed across 6 repositories in GGUF, Transformers and MLX formats, totalling 7.1K downloads.
Specification
- Model name
- lfm3-vl-2b-heretic
- Source repository
- Lucasgitguy-co/lfm3-vl-2b-heretic
- Base model
- LiquidAI/LFM3-VL-2B
- Publisher
- Lucasgitguy-co
- Parameters
- 2B
- VRAM required
- ~1.9 GB at Q4_K_M, 4k context (estimated) — runs on 4 GB cards
- 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
- GGUF, Transformers, MLX
- First indexed
- 28 Oct 2026
- Last updated
- 2 Nov 2026
Ablation technique
How lfm3-vl-2b-heretic 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
“LFM3-VL-2B Heretic checkpoint in Hugging Face Safetensors format, with a language model, vision encoder, projector, tokenizer, processor configuration, and custom model code.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download saidutta69/LFM3-VL-2B-heretic --local-dir ./lfm3-vl-2b-heretic
llama-cli -m ./lfm3-vl-2b-heretic/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "Lucasgitguy-co/lfm3-vl-2b-heretic"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve Lucasgitguy-co/lfm3-vl-2b-heretic --trust-remote-codeDownloads and variants (5)
Every published repository of lfm3-vl-2b-heretic, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| saidutta69/LFM3-VL-2B-heretic | GGUF | 4.3K |
| HydroLabs/LFM3-VL-2B-Heretic-GGUF | GGUF | 1.8K |
| Lucasgitguy-co/lfm3-vl-2b-heretic-gguf | GGUF | 638 |
| Lucasgitguy-co/lfm3-vl-2b-heretic-mlx-4bit | MLX | 242 |
| Lucasgitguy-co/lfm3-vl-2b-hereticsource | Transformers | 118 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- lfm3-vl-2b-heretic 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/LFM3-VL-2B, not added by ablation — at 2B 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 LiquidAI/LFM3-VL-2B’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 lfm3-vl-2b-heretic is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with Lucasgitguy-co, and does not independently verify publisher claims. See responsible use.