LFM2.5-2.6B-Uncensored
2.6BOtheruncensored
from LiquidAI/LFM2.5-2.6B
↓ 17.3K♥ 178 repos
LFM2.5-2.6B-UNCENSORED-ABLITERATED-PHILADELPHIA-CLASS
LFM2.5-2.6B-UNCENSORED-ABLITERATED-PHILADELPHIA-CLASS is a abliterated and uncensored variant of LiquidAI/LFM2.5-2.6B, published on Hugging Face by mradermacher. It is 2.6B parameters, runs on a laptop CPU class and other licence. It is distributed across 6 repositories in GGUF and GGUF (imatrix) formats, totalling 9.2K downloads.
Specification
- Model name
- LFM2.5-2.6B-UNCENSORED-ABLITERATED-PHILADELPHIA-CLASS
- Base model
- LiquidAI/LFM2.5-2.6B
- Publisher
- mradermacher
- Parameters
- 2.6B
- Hardware class
- Under 4B — runs on a laptop CPU
- Licence
- other
- Task
- Text generation
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF, GGUF (imatrix)
- First indexed
- 5 Aug 2026
- Last updated
- 22 Aug 2026
Ablation technique
How LFM2.5-2.6B-UNCENSORED-ABLITERATED-PHILADELPHIA-CLASS 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
“For a convenient overview and download list, visit our model page for this model.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download mradermacher/LFM2.5-2.6B-UNCENSORED-ABLITERATED-PHILADELPHIA-CLASS-GGUF --local-dir ./lfm2.5-2.6b-uncensored-abliterated-philadelphia-class
llama-cli -m ./lfm2.5-2.6b-uncensored-abliterated-philadelphia-class/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "mradermacher/LFM2.5-2.6B-UNCENSORED-ABLITERATED-PHILADELPHIA-CLASS-GGUF"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve mradermacher/LFM2.5-2.6B-UNCENSORED-ABLITERATED-PHILADELPHIA-CLASS-GGUF --trust-remote-codeDownloads and variants (5)
Every published repository of LFM2.5-2.6B-UNCENSORED-ABLITERATED-PHILADELPHIA-CLASS, including quantised re-releases by other authors.
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-UNCENSORED-ABLITERATED-PHILADELPHIA-CLASS 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.
- 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.
- Declared licence is other, 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-UNCENSORED-ABLITERATED-PHILADELPHIA-CLASS is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with mradermacher, and does not independently verify publisher claims. See responsible use.