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

AetherArchitectural/EXAONE-3.5-2.4B-Instruct-abliterated-GGUF-IQ-ARM-Imatrix-Community

AetherArchitectural 2.4B 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-3.5-2.4B-Instruct-abliterated-GGUF-IQ-ARM-Imatrix-Community"
Response includes
  • classification m8
  • files 21
  • hub_downloads_all_time 3,923
  • 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
308 last 30d - cooling
Likes
6
Model age
22mo ago
created 2024-12-18
Downloads over time
Now4K→from286↑1,287%
451.5K2.9K4.3K286 on Dec 18, 20244K on Oct 11Dec '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-3.5-2.4B-Instruct-abliterated this lineage
AetherArchitectural/EXAONE-3.5-2.4B-Instruct-abliterated-GGUF-IQ-ARM-Imatrix-Community↓ 308

Metadata

License
other
Languages
en
Quantizations
BF16 F16 Q3_K Q4 Q4_K Q5_K
Tags
gguf en license:other region:us imatrix conversational

Related

Other by AetherArchitectural
EXAONE-3.5-7.8B-Instruct-abliterated-GGUF-ARM-Imatrix-Community 420
Same base model
mradermacher/EXAONE-3.5-2.4B-Instruct-abliterated-i1-GGUF 557 mradermacher/EXAONE-3.5-2.4B-Instruct-abliterated-GGUF 513 Melvin56/EXAONE-3.5-2.4B-Instruct-abliterated-IQ4_XS-GGUF 29 Impulse2000/EXAONE-3.5-2.4B-Instruct-abliterated-Q8_0-GGUF 22 Shamil12/EXAONE-3.5-2.4B-Instruct-abliterated-IQ4_NL-GGUF 16
Total size
31.2 GB
Files
21
Quantizations
7
Registered
2026-08-22 13:56
Last updated on HF
2024-12-18 01:11
Source huggingface.co/AetherArchitectural/EXAONE-3.5-2.4B-Instruct-abliterated-GGUF-IQ-ARM-Imatrix-Community ↗ Base model huihui-ai/EXAONE-3.5-2.4B-Instruct-abliterated ↗

Files by quantization

BF16 1 file 4.97 GB
EXAONE-3.5-2.4B-Instruct-abliterated-BF16.gguf 4.97 GB 578aeba4 download
F16 1 file 4.97 GB
EXAONE-3.5-2.4B-Instruct-abliterated-F16.gguf 4.97 GB fa42c32e download
Q5_K 2 files 3.52 GB
EXAONE-3.5-2.4B-Instruct-abliterated-Q5_K_M-imat.gguf 1.78 GB 8b2e8838 download
EXAONE-3.5-2.4B-Instruct-abliterated-Q5_K_S-imat.gguf 1.74 GB d8e8bbc1 download
Q4_K 2 files 3.00 GB
EXAONE-3.5-2.4B-Instruct-abliterated-Q4_K_M-imat.gguf 1.53 GB 9a7b078a download
EXAONE-3.5-2.4B-Instruct-abliterated-Q4_K_S-imat.gguf 1.47 GB ea407c26 download
Q4 1 file 1.46 GB
ARM-EXAONE-3.5-2.4B-Instruct-abliterated-Q4_0_4_8-imat.gguf 1.46 GB ffd4b80a download
Q3_K 2 files 2.63 GB
EXAONE-3.5-2.4B-Instruct-abliterated-Q3_K_L-imat.gguf 1.36 GB 5f4cd4e6 download
EXAONE-3.5-2.4B-Instruct-abliterated-Q3_K_M-imat.gguf 1.27 GB 76b26519 download
Auxiliary files 12 files 10.6 GB
EXAONE-3.5-2.4B-Instruct-abliterated-Q8_0-imat.gguf 2.64 GB 5acecd4d download
EXAONE-3.5-2.4B-Instruct-abliterated-Q6_K-imat.gguf 2.04 GB 807f8aa9 download
EXAONE-3.5-2.4B-Instruct-abliterated-IQ4_XS-imat.gguf 1.40 GB b6898529 download
EXAONE-3.5-2.4B-Instruct-abliterated-IQ3_M-imat.gguf 1.20 GB edd96fe3 download
EXAONE-3.5-2.4B-Instruct-abliterated-IQ3_S-imat.gguf 1.17 GB 7966eb4e download
EXAONE-3.5-2.4B-Instruct-abliterated-IQ3_XS-imat.gguf 1.13 GB df01a933 download
EXAONE-3.5-2.4B-Instruct-abliterated-IQ3_XXS-imat.gguf 1.04 GB 1677d172 download
imatrix.dat 2.58 MB 9aea1d40 download
imatrix-with-rp-v3.txt 299 KB fa1ad80c download
LICENSE 13.5 KB 6a427ac3 download
.gitattributes 2.92 KB e0767b5f download
README.md 994 B e9ac0e23 download

README current version from Hugging Face

license: other
license_name: exaone
license_link: LICENSE
language:

  • en
    base_model:
  • huihui-ai/EXAONE-3.5-2.4B-Instruct-abliterated
    inference: false
aetherarchio-flat-banner Check Community Request - #81 for details.

Model name:

EXAONE-3.5-2.4B-Instruct-abliterated

Model link:

https://huggingface.co/huihui-ai/EXAONE-3.5-2.4B-Instruct-abliterated

[!NOTE]
[huihui-ai]

"This is an uncensored version of LGAI-EXAONE/EXAONE-3.5-2.4B-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 2 versions

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

  1. 2024-12-18readmede5c391994 B
    Loading...
  2. 2024-12-18initial commit4b1343b66 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