← back to catalog · registered 2026-10-04 08:58

AX1Y2JP/UniPercept-abliterated-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/AX1Y2JP%2FUniPercept-abliterated-GGUF"
Response includes
  • classification unknown
  • files 14
  • author_summary 2 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
?
Primary method

Unclassified

No clear signals of an abliteration technique in this model.
Confidence
UNKNOWN
Why this label 1 signal
No classification signals present. This may not be an abliterated model at all - it could be a repackaging, a merge with unrelated goals, or unrelated content that mentions the term.
  • no classification signals present (no abliterated, uncensored, or known producer/method markers)
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 · 30-day
267
Likes
0
Model age
7w ago
created 2026-10-04
Downloads over time
Now 1.1K → from 0 ↑ 0%
04148281.2K 0 on Oct 4 1.1K on Nov 22 OctNov
Oct 4 → Nov 22 · 50 snapshots · spans 49 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.

Metadata

License
apache-2.0
Quantizations
BF16 IQ2 IQ3 IQ4 Q3_K Q4 Q4_K Q5_K Q6_K Q8_0
Tags
gguf base_model:Thunderbolt215215/UniPercept base_model:quantized:Thunderbolt215215/UniPercept license:apache-2.0 endpoints_compatible region:us conversational

Related

Total size
56.6 GB
Files
14
Quantizations
11
Registered
2026-10-04 08:58
Last updated on HF
2026-10-04 08:47

Files by quantization

BF16 2 files 14.8 GB
UniPercept-abliterated-BF16.gguf 14.2 GB 8f4d3951 download
mmproj-UniPercept-abliterated-BF16.gguf 636 MB 7f901775 download
Q8_0 1 file 7.54 GB
UniPercept-abliterated-Q8_0.gguf 7.54 GB b393bd31 download
Q6_K 1 file 5.82 GB
UniPercept-abliterated-Q6_K.gguf 5.82 GB a0d38863 download
Q5_K 1 file 5.07 GB
UniPercept-abliterated-Q5_K_M.gguf 5.07 GB 2ae6dc50 download
Q4_K 1 file 4.36 GB
UniPercept-abliterated-Q4_K_M.gguf 4.36 GB 943c3ebd download
Q4 1 file 4.14 GB
UniPercept-abliterated-Q4_0.gguf 4.14 GB 759f331d download
IQ4 1 file 3.93 GB
UniPercept-abliterated-IQ4_XS.gguf 3.93 GB 2838c8dd download
Q3_K 1 file 3.55 GB
UniPercept-abliterated-Q3_K_M.gguf 3.55 GB 7ea5355e download
IQ3 1 file 3.33 GB
UniPercept-abliterated-IQ3_M.gguf 3.33 GB 7dc053ef download
IQ2 2 files 4.70 GB
UniPercept-abliterated-IQ2_M.gguf 2.59 GB 17f07419 download
UniPercept-abliterated-IQ2_XXS.gguf 2.12 GB 4febe0ff download
Auxiliary files 2 files 2.65 KB
.gitattributes 2.31 KB 84e1bde9 download
README.md 344 B c4fa9b09 download

README current version from Hugging Face


license: apache-2.0
base_model:

  • Thunderbolt215215/UniPercept
    base_model_relation: quantized
    library_name: gguf

Please note the following points:

Because it was quantized using unsloth's imatrix, the model's ability to evaluate images may be compromised at low precision.

The lm_head is also subject to quantization.

README history 2 versions

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

  1. 2026-10-04 Update README.md 4e3b792 331 B
    Loading...
  2. 2026-10-04 Upload README.md d8f2096 311 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.

Open in Abliteration