← back to catalog · registered 2026-09-27 21:57

stardude1/LFM2-12B-A1B-SpeedDemon-The-Deckard-II-HERETIC-Uncensored-mlx-4Bit

stardude1 11B MoE 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/stardude1%2FLFM2-12B-A1B-SpeedDemon-The-Deckard-II-HERETIC-Uncensored-mlx-4Bit"
Response includes
  • classification m3
  • files 9
  • hub_downloads_all_time 204
  • author_summary 2 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M3
Primary method

Layer-wise ablation

Applied on top of direct removal inherited from the base model.
Confidence
HIGH
Inherited from base model
Why this label 2 signals
Producer identity confirmed by naming conventions, tags or the model card. This label is very unlikely to change.
  • 'heretic' in model name (Heretic-produced)
  • Heretic uses layer-wise optimization (M3) with underlying direction removal (M1)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
HIGH
Why we say so
name contains 'heretic'; Heretic default extraction is difference-of-means (Arditi 2024)
Downloads · lifetime
204
Likes
0
Model age
7w ago
created 2026-09-27
Downloads over time
Now 641 → from 0 ↑ 0%
0235470705 0 on Sep 27 641 on Nov 22 SepOctNov
Sep 27 → Nov 22 · 57 snapshots · spans 56 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
apache-2.0
Languages
en
Tags
transformers safetensors lfm2_moe text-generation finetune unsloth mixture of experts sparse moe moe heretic uncensored aliterated

Related

Total size
5.91 GB
Files
9
Quantizations
1
Registered
2026-09-27 21:57
Last updated on HF
2026-09-27 21:24

Files by quantization

Auxiliary files 9 files 5.92 GB
model-00001-of-00002.safetensors 4.96 GB afacf89a download
model-00002-of-00002.safetensors 978 MB a7dcc99e download
tokenizer.json 4.51 MB 3062743c download
model.safetensors.index.json 67.7 KB 99e7acb9 download
config.json 8.18 KB ea818e96 download
README.md 1.60 KB f8123069 download
.gitattributes 1.48 KB a6344aac download
chat_template.jinja 1.27 KB 99f3593d download
tokenizer_config.json 549 B bce40c4d download

README current version from Hugging Face


base_model: DavidAU/LFM2-12B-A1B-SpeedDemon-The-Deckard-II-HERETIC-Uncensored
license: apache-2.0
language:

  • en
    pipeline_tag: text-generation
    library_name: transformers
    tags:
  • finetune
  • unsloth
  • mixture of experts
  • sparse moe
  • moe
  • heretic
  • uncensored
  • aliterated
  • all use cases
  • coder
  • creative
  • creative writing
  • fiction writing
  • plot generation
  • sub-plot generation
  • story generation
  • scene continue
  • storytelling
  • fiction story
  • science fiction
  • romance
  • all genres
  • story
  • writing
  • vivid prosing
  • vivid writing
  • fiction
  • roleplaying
  • bfloat16
  • mlx
  • mlx-my-repo

stardude1/LFM2-12B-A1B-SpeedDemon-The-Deckard-II-HERETIC-Uncensored-mlx-4Bit

The Model stardude1/LFM2-12B-A1B-SpeedDemon-The-Deckard-II-HERETIC-Uncensored-mlx-4Bit was converted to MLX format from DavidAU/LFM2-12B-A1B-SpeedDemon-The-Deckard-II-HERETIC-Uncensored using mlx-lm version 0.31.2.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("stardude1/LFM2-12B-A1B-SpeedDemon-The-Deckard-II-HERETIC-Uncensored-mlx-4Bit")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)

README history 1 version

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

  1. 2026-09-27 Upload folder using huggingface_hub 849b0af 1.6 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