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

AetherArchitectural/EXAONE-3.5-7.8B-Instruct-abliterated-GGUF-ARM-Imatrix-Community

AetherArchitectural 7.8B GGUF second-order 33K 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/AetherArchitectural%2FEXAONE-3.5-7.8B-Instruct-abliterated-GGUF-ARM-Imatrix-Community"
Response includes
  • classification m8
  • files 19
  • hub_downloads_all_time 4,136
  • author_summary 2 models
  • readme_text full
Try next
GET/models?author=AetherArchitectural
All 2 models by AetherArchitectural
 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 · lifetime
4K
420 last 30d - stable
Likes
7
Model age
22mo ago
created 2024-12-19
Downloads over time
Now4.2K→from132↑3,100%
01.5K3.1K4.6K132 on Dec 18, 20244.2K on Oct 114.2K on Oct 10Dec '24Mar '25Jun '25Sep '25Dec '25MarJunSep
Dec 18, 2024 → Oct 11 · 134 snapshots · spans 662 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.

huihui-ai/EXAONE-3.5-7.8B-Instruct-abliterated this lineage
AetherArchitectural/EXAONE-3.5-7.8B-Instruct-abliterated-GGUF-ARM-Imatrix-Community↓ 420

Metadata

License
other
Languages
en
Quantizations
Q3_K Q4 Q4_K Q5_K
Tags
gguf en license:other region:us imatrix conversational

Related

Other by AetherArchitectural
EXAONE-3.5-2.4B-Instruct-abliterated-GGUF-IQ-ARM-Imatrix-Community 308
Same base model
mradermacher/EXAONE-3.5-7.8B-Instruct-abliterated-i1-GGUF 619 mradermacher/EXAONE-3.5-7.8B-Instruct-abliterated-GGUF 349 DevQuasar-5/huihui-ai.EXAONE-3.5-7.8B-Instruct-abliterated-GGUF 191 BernTheCreator/EXAONE-3.5-7.8B-Instruct-abliterated-Q4_0-GGUF 43 Melvin56/EXAONE-3.5-7.8B-Instruct-abliterated-IQ4_XS-GGUF 20
Total size
61.2 GB
Files
19
Quantizations
5
Registered
2026-08-22 13:56
Last updated on HF
2024-12-19 19:37
Source huggingface.co/AetherArchitectural/EXAONE-3.5-7.8B-Instruct-abliterated-GGUF-ARM-Imatrix-Community ↗ Base model huihui-ai/EXAONE-3.5-7.8B-Instruct-abliterated ↗

Files by quantization

Q5_K 2 files 10.2 GB
EXAONE-3.5-7.8B-Instruct-abliterated-Q5_K_M-imat.gguf 5.19 GB 82c8c492 download
EXAONE-3.5-7.8B-Instruct-abliterated-Q5_K_S-imat.gguf 5.06 GB a0c78a5b download
Q4_K 2 files 8.67 GB
EXAONE-3.5-7.8B-Instruct-abliterated-Q4_K_M-imat.gguf 4.44 GB 2eb5164e download
EXAONE-3.5-7.8B-Instruct-abliterated-Q4_K_S-imat.gguf 4.23 GB f718eacb download
Q4 1 file 4.20 GB
EXAONE-3.5-7.8B-Instruct-abliterated-Q4_0_4_8-imat.gguf 4.20 GB 95664215 download
Q3_K 2 files 7.51 GB
EXAONE-3.5-7.8B-Instruct-abliterated-Q3_K_L-imat.gguf 3.90 GB 9d1cd51e download
EXAONE-3.5-7.8B-Instruct-abliterated-Q3_K_M-imat.gguf 3.62 GB 566375af download
Auxiliary files 12 files 30.5 GB
EXAONE-3.5-7.8B-Instruct-abliterated-Q8_0-imat.gguf 7.74 GB 40e065a9 download
EXAONE-3.5-7.8B-Instruct-abliterated-Q6_K-imat.gguf 5.98 GB b793864c download
EXAONE-3.5-7.8B-Instruct-abliterated-IQ4_XS-imat.gguf 4.01 GB 336a0b63 download
EXAONE-3.5-7.8B-Instruct-abliterated-IQ3_M-imat.gguf 3.40 GB fbb26352 download
EXAONE-3.5-7.8B-Instruct-abliterated-IQ3_S-imat.gguf 3.30 GB b39c5091 download
EXAONE-3.5-7.8B-Instruct-abliterated-IQ3_XS-imat.gguf 3.15 GB 5b212aa0 download
EXAONE-3.5-7.8B-Instruct-abliterated-IQ3_XXS-imat.gguf 2.94 GB 134939e1 download
imatrix.dat 4.76 MB 8887a3cf download
imatrix-with-rp-v3.txt 299 KB fa1ad80c download
LICENSE 13.5 KB 6a427ac3 download
.gitattributes 2.76 KB 1b3cfe4e download
README.md 994 B 1e38ff70 download

README current version from Hugging Face

license: other
license_name: exaone
license_link: LICENSE
language:

  • en
    base_model:
  • huihui-ai/EXAONE-3.5-7.8B-Instruct-abliterated
    inference: false
aetherarchio-flat-banner Check Community Request - #82 for details.

Model name:

EXAONE-3.5-2.4B-Instruct-abliterated

Model link:

https://huggingface.co/huihui-ai/EXAONE-3.5-7.8B-Instruct-abliterated

[!NOTE]
[huihui-ai]

"This is an uncensored version of LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct created with abliteration (see remove-refusals-with-transformers to know more about it).
This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens."

README history 1 version

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

  1. 2024-12-19Create README.mda524e36994 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