Get the app
← back to catalog · registered 2026-08-22 13:56

dummy9996/LFM2.5-230M-abliterated1-gguf

dummy9996 Lfm GGUF
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/dummy9996%2FLFM2.5-230M-abliterated1-gguf"
Response includes
  • classification m8
  • files 3
  • author_summary 17 models
  • readme_text full
Try next
GET/models?author=dummy9996
All 17 models by dummy9996
 GET/models?family=lfm&method=m8
Sibling lfm models · same method
 GET/methods/m8
What "m8" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

Applied on top of direct removal inherited from the base model.
Confidence
MEDIUM
Inherited from base model
M1 Direct removal →
Why this label 3 signals
Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.
  • 'abliterated' in name/tags
  • is_gguf=1
  • assume M1 (base ablation) + M8 (GGUF quant) - default when producer unknown
How we label → About M8 →
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
22
↑ 147% in 90 days
Likes
0
Model age
3mo ago
created 2026-06-29
Downloads over time
Now476→from193↑147%
179287396504193 on Jul 1476 on Sep 10476 on Sep 2JulAugSep
Jul 1 → Sep 10 · 23 snapshots · spans 71 days

Variants by this author 2 formats · 23 downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

Quantizations
BF16
Tags
gguf text-generation base_model:dummy9996/LFM2.5-230M-abliterated1 base_model:quantized:dummy9996/LFM2.5-230M-abliterated1 endpoints_compatible region:us conversational

Related

Other by dummy9996
Qwen2.5-VL-7B-abliterated_nvfp4_int8convrot_comfyui 575 Uncensored-Ministral-3-3B-gguf 223 Qwen3-VL-4B-Instruct-Uncensored-abliterated-gguf 218 Qwen3-VL-4B-Instruct-Uncensored-abliterated 168 qwen3_8b_abliterated_nvfp4-comfyui 113
Total size
568 MB
Files
3
Quantizations
2
Registered
2026-08-22 13:56
Last updated on HF
2026-07-05 13:57
Source huggingface.co/dummy9996/LFM2.5-230M-abliterated1-gguf ↗

Files by quantization

BF16 1 file 568 MB
LFM2.5-230M-abliterated-bf16.gguf 568 MB 4cfb5990 download
Auxiliary files 2 files 1.77 KB
.gitattributes 1.69 KB 7a8a4db8 download
README.md 86.0 B cbdfc4e0 download

README current version from Hugging Face

pipeline_tag: text-generation
base_model:

  • dummy9996/LFM2.5-230M-abliterated1

README history 1 version

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

  1. 2026-06-29Super-squash branch 'main' using huggingface_hub606b37a86 B
    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.

Get the app Browse the catalog
Open in Abliteration