← back to catalog · registered 2026-11-12 14:03

NeosQ/LFM3-Omni-2B-Uncensored-ARA.gguf

NeosQ 2B GGUF multimodal second-order
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/NeosQ%2FLFM3-Omni-2B-Uncensored-ARA.gguf"
Response includes
  • classification m-uncensored
  • files 8
  • author_summary 6 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · 30-day
190
Likes
0
Model age
1w ago
created 2026-11-12
Downloads over time
Now 190 → from 0 ↑ 0%
070139209 0 on Nov 12 190 on Nov 22 190 on Nov 21 Nov
Nov 12 → Nov 22 · 11 snapshots · spans 10 days

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

Metadata

License
other
Quantizations
BF16 Q4_K Q8_0
Tags
gguf llama.cpp lfm3 lfm3-omni abliteration uncensored refusal-removal audio vision speech q4_k_m q8_0

Related

Total size
6.20 GB
Files
8
Quantizations
5
Registered
2026-11-12 14:03
Last updated on HF
2026-11-12 07:23

Files by quantization

BF16 1 file 3.23 GB
LFM3-Omni-2B-Uncensored-ARA-BF16.gguf 3.23 GB a2e75993 download
Q8_0 1 file 1.95 GB
LFM3-Omni-2B-Uncensored-ARA-Q8_0.gguf 1.95 GB fbf084e7 download
Q4_K 1 file 1.02 GB
LFM3-Omni-2B-Uncensored-ARA-Q4_K_M.gguf 1.02 GB 82bfe935 download
F16 1 file 906 MB
mmproj-LFM3-Omni-2B-Uncensored-ARA-F16.gguf 906 MB fa273ed3 download
Auxiliary files 4 files 22.1 KB
LICENSE 10.3 KB 25e731c6 download
README.md 5.13 KB 180208d0 download
README_zh.md 4.87 KB a6213c9c download
.gitattributes 1.78 KB 090e1a65 download

README current version from Hugging Face


library_name: gguf
pipeline_tag: any-to-any
license: other
license_name: lfm1.0
license_link: LICENSE
base_model: NeosQ/LFM3-Omni-2B-Uncensored-ARA
tags:

  • gguf
  • llama.cpp
  • lfm3
  • lfm3-omni
  • abliteration
  • uncensored
  • refusal-removal
  • audio
  • vision
  • speech
  • q4_k_m
  • q8_0

LFM3-Omni-2B-Uncensored-ARA.gguf

中文说明 / Chinese README

Research-only, no refusal guardrail. This is an abliterated checkpoint: it will answer
requests the base model declines and can produce unsafe or illegal content. Not for
production or consumer-facing use. You are responsible for what you generate.

GGUF conversion of NeosQ/LFM3-Omni-2B-Uncensored-ARA, which is
LiquidAI/LFM3-Omni-2B with its refusal direction removed using ARA (Arbitrary-Rank Ablation).
Three quantisation levels plus the multimodal projector, all in one repo.

Text backbone and projector are separate files. The *gguf main file is text-only on its
own; pass the mmproj-* file with -mm / --mmproj to get image input, audio input and speech
output. Both are required for anything multimodal.

Files

File Size Tensors Notes
LFM3-Omni-2B-Uncensored-ARA-BF16.gguf 3.2 GiB 287 unquantised export, reference file
LFM3-Omni-2B-Uncensored-ARA-Q8_0.gguf 1.9 GiB 287 8-bit, token embedding kept in F16
LFM3-Omni-2B-Uncensored-ARA-Q4_K_M.gguf 1.0 GiB 287 stock k-quant, the one to grab for laptops
mmproj-LFM3-Omni-2B-Uncensored-ARA-F16.gguf 905.8 MiB 458 vision + audio encoder, depthformer and codec — required for image/audio in and speech out

Q4_K_M is the default pick: ~1 GB and it keeps the text quality you would expect at 4-bit.
Take Q8_0 if you have the RAM and want the closest match to the BF16 export. BF16 is
included as the exact reference the others were quantised from.

Requirements

A llama.cpp build with LFM3 / LFM3-Omni support. These files were produced and tested at
build b1-09338b8; older builds fail with unknown model architecture: 'lfm3'.

git clone https://github.com/ggml-org/llama.cpp && cd llama.cpp
cmake -B build -DCMAKE_BUILD_TYPE=Release && cmake --build build -j

Usage

Text only:

llama-cli -m LFM3-Omni-2B-Uncensored-ARA-Q4_K_M.gguf -p "Explain what a mixture-of-experts layer does." -n 256

Image, audio, video or speech output (projector required):

llama-mtmd-cli -m LFM3-Omni-2B-Uncensored-ARA-Q4_K_M.gguf \
  --mmproj mmproj-LFM3-Omni-2B-Uncensored-ARA-F16.gguf \
  --image photo.jpg -p "Describe the image in one sentence."
llama-mtmd-cli -m LFM3-Omni-2B-Uncensored-ARA-Q4_K_M.gguf --mmproj mmproj-LFM3-Omni-2B-Uncensored-ARA-F16.gguf \
  --audio speech.wav -p "" --temp 0 -sys "Perform ASR in English."

Server:

llama-server -m LFM3-Omni-2B-Uncensored-ARA-Q4_K_M.gguf --mmproj mmproj-LFM3-Omni-2B-Uncensored-ARA-F16.gguf --port 8080

The model is non-reasoning; --reasoning off keeps llama-server from wrapping answers.

Long-form output

This is a 2B model and long answers are its weak spot. With llama.cpp defaults it loops,
drifts into code or collapses into an outline. The settings that fixed it on the transformers
build (repetition_penalty=1.3 over a 1024-token window, temperature=1.0, top_p=0.95) map
to:

llama-cli -m LFM3-Omni-2B-Uncensored-ARA-Q4_K_M.gguf --temp 1.0 --top-p 0.95 \
  --repeat-penalty 1.3 --repeat-last-n 1024 -n 1600

--repeat-last-n is the equivalent of the model's text_repetition_window; the default 64 is
shorter than one sentence, which is why paragraphs get copied verbatim. One pass reliably
holds 800-2,000 characters; longer text needs section-by-section generation. The full
measurements are in the transformers model card.

How these were made

Step Tool Result
Convert backbone convert_hf_to_gguf.py --outtype bf16 BF16, 287 tensors
Convert projector convert_hf_to_gguf.py --outtype f16 --mmproj F16, 458 tensors
Q8_0 llama-quantize --token-embedding-type F16 8-bit, embedding untouched
Q4_K_M llama-quantize stock preset no imatrix, no custom mix

No retraining and no calibration data: these are direct quantisations of the BF16 export.
Multimodal was verified end-to-end (llama-mtmd-cli with an image prompt) and all four files
load in llama-cli; per-file SHA-256:

a2e759935dbff2eb066769bcbecd7fd83536fd20bf4c9c54bcf4a3342871f150  LFM3-Omni-2B-Uncensored-ARA-BF16.gguf
fbf084e79830605007485908969f0f40d2951508beba58dd2e64149e64762870  LFM3-Omni-2B-Uncensored-ARA-Q8_0.gguf
82bfe935b0773f7fbf250a41112f5224998fcde27f71df65617d371d2ed18873  LFM3-Omni-2B-Uncensored-ARA-Q4_K_M.gguf
fa273ed3c1ee56cad530a5d4415c379b0958b31f9727c1808d420edcaa0468cf  mmproj-LFM3-Omni-2B-Uncensored-ARA-F16.gguf

License

LFM Open License v1.0, inherited from LiquidAI/LFM3-Omni-2B (see LICENSE). All of its
terms, including the commercial-use threshold, apply to this derivative and to these GGUF
files. Community conversion, not affiliated with or endorsed by Liquid AI.

README history 1 version

The author's README evolved over time. Click a version to see its content at that point.

  1. 2026-11-12 Upload folder using huggingface_hub 61e4038 5.1 KB
    Loading...
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Open in Abliteration