LFM3-1.7B-Heretic-Abliterated
1.7BOtherheretic
from LiquidAI/LFM3-1.7B
↓ 23.5K♥ 174 repos
LFM3-1.7B-Uncensored
LFM3-1.7B-Uncensored is a abliterated and uncensored variant of LiquidAI/LFM3-1.7B, published on Hugging Face by OpenIntelligenceNet. It is 1.7B parameters and runs on a laptop CPU class. It is distributed across 6 repositories in Transformers, MLX and GGUF formats, totalling 85.8K downloads.
Specification
- Model name
- LFM3-1.7B-Uncensored
- Source repository
- OpenIntelligenceNet/LFM3-1.7B-Uncensored
- Base model
- LiquidAI/LFM3-1.7B
- Publisher
- OpenIntelligenceNet
- Parameters
- 1.7B
- VRAM required
- ~1.7 GB at Q4_K_M, 4k context (estimated) — runs on 4 GB cards
- Hardware class
- Under 4B — runs on a laptop CPU
- Licence
- Not declared
- Task
- Text generation
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- Transformers, MLX, GGUF
- First indexed
- 27 Oct 2026
- Last updated
- 3 Nov 2026
Ablation technique
How LFM3-1.7B-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
“OpenIntelligenceNet/LFM3-1.7B-Uncensored is an uncensored, directional-abliterated variant of LiquidAI/LFM3-1.7B created using Heretic (v2.0.0.dev0).”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download AtomicChat/LFM3-1.7B-Uncensored-GGUF --local-dir ./lfm3-1.7b-uncensored
llama-cli -m ./lfm3-1.7b-uncensored/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "OpenIntelligenceNet/LFM3-1.7B-Uncensored"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve OpenIntelligenceNet/LFM3-1.7B-Uncensored --trust-remote-codeDownloads and variants (5)
Every published repository of LFM3-1.7B-Uncensored, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| AtomicChat/LFM3-1.7B-Uncensored-GGUF | GGUF | 84.2K |
| OpenIntelligenceNet/LFM3-1.7B-Uncensoredsource | Transformers | 838 |
| mchen04/LFM3-1.7B-Uncensored-MLX | MLX | 341 |
| Centerjon/LFM3-1.7B-Uncensored-GGUF | GGUF | 323 |
| nekonishin/LFM3-1.7B-Uncensored-GGUF | GGUF | 145 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- LFM3-1.7B-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.
- Capability is inherited from LiquidAI/LFM3-1.7B, not added by ablation — at 1.7B 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.
- 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.
- No licence is declared on this repository, which is a compliance problem in itself. Resolve it against the base model’s terms before use.
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 LFM3-1.7B-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 OpenIntelligenceNet, and does not independently verify publisher claims. See responsible use.