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

matrixportalx/lenML-aya-expanse-8b-abliterated-GGUF

matrixportalx 8B GGUF 8K 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/matrixportalx%2FlenML-aya-expanse-8b-abliterated-GGUF"
Response includes
  • classification m8
  • files 3
  • hub_downloads_all_time 420
  • author_summary 44 models
  • readme_text full
Try next
GET/models?author=matrixportalx
All 44 models by matrixportalx
 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
420
22 last 30d - cooling
Likes
2
Model age
16mo ago
created 2025-05-20
Downloads over time
Now423→from175↑142%
163258353448175 on Jul 30, 2025423 on Oct 11423 on Oct 7Jul '25Sep '25Nov '25JanMarMayJulSep
Jul 30, 2025 → Oct 11 · 102 snapshots · spans 438 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.

CohereForAI/aya-expanse-8b this lineage
matrixportalx/lenML-aya-expanse-8b-abliterated-GGUF↓ 22

Metadata

License
cc-by-nc-4.0
Languages
en fr de es it pt ja ko zh ar el fa pl id cs he hi nl ro ru tr uk vi
Tags
transformers gguf CohereForAI en fr de es it pt ja ko zh

Related

Other by matrixportalx
gemma-3-4b-it-abliterated-GGUF 1K gemma-3-1b-it-abliterated-GGUF 728 gemma-3-12b-it-abliterated-GGUF 537 DeepSeek-R1-Distill-Llama-8B-Abliterated-GGUF 306 L3.1-Dark-Planet-SpinFire-Uncensored-8B-GGUF 218
Same base model
lenML/aya-expanse-8b-abliterated 264
Total size
4.71 GB
Files
3
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-05-20 02:25
Source huggingface.co/matrixportalx/lenML-aya-expanse-8b-abliterated-GGUF ↗ Base model CohereForAI/aya-expanse-8b ↗

Files by quantization

Auxiliary files 3 files 4.71 GB
aya-expanse-8b-abliterated.q4_k_m.gguf 4.71 GB e4905b72 download
.gitattributes 1.56 KB ab65f377 download
README.md 975 B 3e70a05e download

README current version from Hugging Face

inference: false
library_name: transformers
language:

  • en
  • fr
  • de
  • es
  • it
  • pt
  • ja
  • ko
  • zh
  • ar
  • el
  • fa
  • pl
  • id
  • cs
  • he
  • hi
  • nl
  • ro
  • ru
  • tr
  • uk
  • vi
    license: cc-by-nc-4.0
    base_model:
  • CohereForAI/aya-expanse-8b
    tags:
  • gguf
  • CohereForAI

aya-expanse-8b-abliterated GGUF Quantized Models

Technical Details

  • Quantization Tool: llama.cpp
  • Version: version: 5427 (f7c9429c)

Model Information

Available Files

🚀 Download 🔢 Type 📝 Description
Download Q4 K M 4-bit balanced (recommended default)

💡 Q4 K M provides the best balance for most use cases

README history 1 version

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

  1. 2025-05-20Upload README.md with huggingface_hub645484a975 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