← back to catalog · registered 2026-10-17 03:59

mradermacher/LFM2.5-24B-A2B-Uncensored-Heretic-GGUF

mradermacher 24B 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/mradermacher%2FLFM2.5-24B-A2B-Uncensored-Heretic-GGUF"
Response includes
  • classification m3
  • files 9
  • author_summary 3349 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 · 30-day
0
Likes
0
Model age
today
created 2026-10-17

Metadata

Quantizations
Q2_K Q3_K Q4_K Q6_K Q8_0
Tags
gguf endpoints_compatible region:us conversational

Related

Total size
95.0 GB
Files
9
Quantizations
6
Registered
2026-10-17 03:59
Last updated on HF
2026-10-17 03:55

Files by quantization

Q8_0 1 file 23.7 GB
LFM2.5-24B-A2B-Uncensored-Heretic.Q8_0.gguf 23.7 GB b46d92ad download
Q6_K 1 file 18.3 GB
LFM2.5-24B-A2B-Uncensored-Heretic.Q6_K.gguf 18.3 GB ad03e4e8 download
Q4_K 1 file 12.7 GB
LFM2.5-24B-A2B-Uncensored-Heretic.Q4_K_S.gguf 12.7 GB 10f6dc1b download
Q3_K 3 files 32.0 GB
LFM2.5-24B-A2B-Uncensored-Heretic.Q3_K_L.gguf 11.6 GB 3a928765 download
LFM2.5-24B-A2B-Uncensored-Heretic.Q3_K_M.gguf 10.7 GB d15b9c3c download
LFM2.5-24B-A2B-Uncensored-Heretic.Q3_K_S.gguf 9.71 GB a77d693e download
Q2_K 1 file 8.20 GB
LFM2.5-24B-A2B-Uncensored-Heretic.Q2_K.gguf 8.20 GB d9fae7c1 download
Auxiliary files 2 files 2.42 KB
.gitattributes 2.04 KB 65cc83d9 download
README.md 388 B aa0b77ef download

README current version from Hugging Face

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