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

Spaceballs/Llama-3.1-8B-Lexi-Uncensored-V2-heretic-GGUF

Spaceballs Llama 8B GGUF second-order 131K ctx
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/Spaceballs%2FLlama-3.1-8B-Lexi-Uncensored-V2-heretic-GGUF"
Response includes
  • classification m3
  • files 7
  • hub_downloads_all_time 3,203
  • author_summary 5 models
  • readme_text full
Try next
GET/models?author=Spaceballs
All 5 models by Spaceballs
 GET/models?family=llama&method=m3
Sibling llama models · same method
 GET/methods/m3
What "m3" means · taxonomy
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
M1 Direct removal →
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)
How we label → About M3 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
HIGH
Why we say so
name contains 'heretic'; Heretic default extraction is difference-of-means (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
3K
628 last 30d - stable
Likes
0
Model age
4mo ago
created 2026-05-30
Downloads over time
Now3.3K→from501↑550%
3631.4K2.5K3.5K501 on Jun 103.3K on Oct 11JunJulAugSepOct
Jun 10 → Oct 11 · 57 snapshots · spans 123 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.

Spaceballs/Llama-3.1-8B-Lexi-Uncensored-V2-heretic↓ 20 this lineage
Spaceballs/Llama-3.1-8B-Lexi-Uncensored-V2-heretic-GGUF↓ 628

Variants by this author 2 formats · 648 downloads combined

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

Metadata

License
llama3.1
Quantizations
F16 Q4_K Q6_K Q8_0
Tags
gguf GGUF Llama quantization heretic uncensored decensored abliterated obliterated ablated derestricted jail

Related

Other by Spaceballs
Llama-3.1-8B-Lexi-Uncensored-V2-apostate-GGUF 188 Llama-3.1-8B-Lexi-Uncensored-V2-Q6_K-GGUF 89 Llama-3.1-8B-Lexi-Uncensored-V2-heretic 20 Llama-3.1-8B-Lexi-Uncensored-V2-apostate 0
Total size
33.6 GB
Files
7
Quantizations
5
Registered
2026-08-22 13:56
Last updated on HF
2026-06-05 00:31
Source huggingface.co/Spaceballs/Llama-3.1-8B-Lexi-Uncensored-V2-heretic-GGUF ↗ Base model Spaceballs/Llama-3.1-8B-Lexi-Uncensored-V2-heretic →

Files by quantization

F16 1 file 15.0 GB
Llama-3.1-8B-Lexi-Uncensored-V2-heretic-f16.gguf 15.0 GB 3dc1682b download
Q8_0 1 file 7.95 GB
Llama-3.1-8B-Lexi-Uncensored-V2-heretic-Q8_0.gguf 7.95 GB e22a0934 download
Q6_K 1 file 6.14 GB
Llama-3.1-8B-Lexi-Uncensored-V2-heretic-Q6_K.gguf 6.14 GB f1e20572 download
Q4_K 1 file 4.58 GB
Llama-3.1-8B-Lexi-Uncensored-V2-heretic-Q4_K_M.gguf 4.58 GB 98313161 download
Auxiliary files 3 files 113 KB
lol.png 111 KB deb45492 download
.gitattributes 1.61 KB 17fa3290 download
README.md 813 B f88e2953 download

README current version from Hugging Face

library_name: gguf
tags:

  • GGUF
  • Llama
  • quantization
  • heretic
  • uncensored
  • decensored
  • abliterated
  • obliterated
  • ablated
  • derestricted
  • jail
  • jailbroke
  • jailbreak
  • jailbroken
    base_model:
  • Spaceballs/Llama-3.1-8B-Lexi-Uncensored-V2-heretic
    license: llama3.1
    pipeline_tag: text-generation

quants generated from: https://huggingface.co/Spaceballs/Llama-3.1-8B-Lexi-Uncensored-V2-heretic
image/png
Yes this is an uncensoring of an already uncensored model 🤪 the original model was uncensored using Unsloth, and this was further uncensored using Heretic.

README history 9 versions

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

  1. 2026-06-05Update README.md12c9742813 B
    Loading...
  2. 2026-06-03Update README.md3ea9a08777 B
    Loading...
  3. 2026-06-03Update README.md9f63d30622 B
    Loading...
  4. 2026-05-31Update README.mdaa509f9464 B
    Loading...
  5. 2026-05-31Update README.mda30baaf236 B
    Loading...
  6. 2026-05-31Update README.mdc0e1e91226 B
    Loading...
  7. 2026-05-31Update README.md8c65c8f226 B
    Loading...
  8. 2026-05-31Update README.md32b50b0112 B
    Loading...
  9. 2026-05-31Create README.md30032e487 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