LFM2.5-8B-A1B-abliterated
8BOther
from LiquidAI/LFM2.5-8B-A1B
↓ 8.3K♥ 917 repos
LFM2.5-8B-A1B-Uncensored-Gaston
LFM2.5-8B-A1B-Uncensored-Gaston is a abliterated and uncensored variant of LiquidAI/LFM2.5-8B-A1B, published on Hugging Face by gaston-parravicini. It is 8B total parameters (mixture-of-experts), single consumer GPU class and other licence. It is distributed across 3 repositories in GGUF format, totalling 8.3K downloads.
Specification
- Model name
- LFM2.5-8B-A1B-Uncensored-Gaston
- Source repository
- gaston-parravicini/LFM2.5-8B-A1B-Uncensored-Gaston-GGUF
- Base model
- LiquidAI/LFM2.5-8B-A1B
- Publisher
- gaston-parravicini
- Parameters
- 8B (mixture-of-experts)
- Hardware class
- 4B – 10B — single consumer GPU
- Licence
- other
- Task
- Text generation
- Context window
- 128K tokens (as documented)
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF
- First indexed
- 30 May 2026
- Last updated
- 20 Aug 2026
Ablation technique
How LFM2.5-8B-A1B-Uncensored-Gaston 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
“LFM2.5-8B-A1B is Liquid AI's latest edge model — a hybrid convolution + attention MoE architecture with:”
Running it
Commands are templates — confirm the exact repository and quant file before use.
Ollama (publisher-documented)
ollama run hf.co/gaston-parravicini/LFM2.5-8B-A1B-Uncensored-Gaston-GGUF:Q4_K_Mllama.cpp / GGUF
hf download gaston-parravicini/LFM2.5-8B-A1B-Uncensored-Gaston-GGUF --local-dir ./lfm2.5-8b-a1b-uncensored-gaston
llama-cli -m ./lfm2.5-8b-a1b-uncensored-gaston/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "gaston-parravicini/LFM2.5-8B-A1B-Uncensored-Gaston-GGUF"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve gaston-parravicini/LFM2.5-8B-A1B-Uncensored-Gaston-GGUF --trust-remote-codeDownloads and variants (2)
Every published repository of LFM2.5-8B-A1B-Uncensored-Gaston, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| gaston-parravicini/LFM2.5-8B-A1B-Uncensored-Gaston-GGUFsource | GGUF | 7.8K |
| Justbackup/LFM2.5-8B-A1B-Uncensored-Gaston-GGUF | GGUF | 516 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- LFM2.5-8B-A1B-Uncensored-Gaston 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/LFM2.5-8B-A1B, not added by ablation — at 8B 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/LFM2.5-8B-A1B’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 LFM2.5-8B-A1B-Uncensored-Gaston is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with gaston-parravicini, and does not independently verify publisher claims. See responsible use.