← back to catalog · registered 2026-10-04 22:58

Anotos/LFM2-8B-A1B-Abliterated-MLX-4bit

Name: Anotos/LFM2-8B-A1B-Abliterated-MLX-4bit
Author: Anotos

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/Anotos%2FLFM2-8B-A1B-Abliterated-MLX-4bit"

Response includes

classification m-uncensored
files 9
author_summary 1 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.

Downloads · 30-day

Likes

Model age

today

created 2026-10-04

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.

huihui-ai/Huihui-LFM2-8B-A1B-abliterated↓ 141 this lineage

Anotos/LFM2-8B-A1B-Abliterated-MLX-4bit

Metadata

License

other

Files by quantization

Auxiliary files 9 files 4.37 GB

model.safetensors	4.37 GB	6d751b1f	download
tokenizer.json	4.51 MB	3062743c	download
LICENSE	10.3 KB	25e731c6	download
config.json	6.12 KB	06870a53	download
README.md	1.58 KB	91daa5c2	download
.gitattributes	1.48 KB	a6344aac	download
chat_template.jinja	1.27 KB	99f3593d	download
tokenizer_config.json	552 B	cfff92de	download
generation_config.json	137 B	b946d67b	download

README current version from Hugging Face

library_name: mlx
license: other
license_name: lfm1.0
license_link: LICENSE
base_model:

huihui-ai/Huihui-LFM2-8B-A1B-abliterated
pipeline_tag: text-generation
tags:
mlx
liquid
lfm2
moe
abliterated
uncensored

LFM2 8B-A1B abliterated, MLX 4-bit

An MLX 4-bit conversion of huihui-ai/Huihui-LFM2-8B-A1B-abliterated (commit 4f832b42af), for Apple Silicon.

This is an abliterated ("uncensored") version of Liquid AI's LFM2 8B-A1B: it has been modified to refuse less. It is a mixture-of-experts model with 8.3B parameters in total and about 1.5B active per token.

What was changed

Converted and quantized with mlx-lm 0.32.0:

mlx_lm.convert --hf-path huihui-ai/Huihui-LFM2-8B-A1B-abliterated -q --q-bits 4

4-bit weights (4.5 bits per weight overall, group size 64), with the expert routing gates kept at 8 bits. No other changes. The file is 4.69 GB.

model.safetensors SHA-256: 6d751b1f18fe365881d46df1f7f715f10fb2fbab0ffd065cc3df374c4cdf9457

Use

mlx_lm.generate --model Anotos/LFM2-8B-A1B-Abliterated-MLX-4bit --prompt "..."

In MLX Swift use mlx-swift-lm 3.31.4 or later; earlier versions route this model's experts incorrectly.

Credits and license

Model: LiquidAI/LFM2-8B-A1B by Liquid AI.
Abliteration: huihui-ai.
MLX conversion: Axly's Customs, for the Erato app.

LFM Open License v1.0; see LICENSE. Commercial use is limited to organisations under the revenue threshold in the license.

Anotos/LFM2-8B-A1B-Abliterated-MLX-4bit

The browser can't see your hardware

The Abliteration app is integrated with your machine

And you can chat with any model, right now

Uncensored (method unknown)

Genealogy 0 direct forks

Metadata

Related

Files by quantization

README current version from Hugging Face

LFM2 8B-A1B abliterated, MLX 4-bit

What was changed

Use

Credits and license

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