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

failspy/kappa-3-phi-3-4k-instruct-abliterated-GGUF

failspy Phi GGUF 4K 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/failspy%2Fkappa-3-phi-3-4k-instruct-abliterated-GGUF"
Response includes
  • classification m8
  • files 3
  • hub_downloads_all_time 8,697
  • author_summary 21 models
  • readme_text full
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
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
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
9K
32 last 30d - cooling
Likes
12
Model age
2.4y ago
created 2024-05-06
Downloads over time
Now8.7K→from1K↑746%
03.2K6.4K9.6K1K on Jul 24, 20248.7K on Oct 118.7K on Oct 10Jul '24Nov '24Mar '25Jul '25Nov '25MarJul
Jul 24, 2024 → Oct 11 · 155 snapshots · spans 809 days

Metadata

License
mit
Quantizations
F16
Tags
gguf license:mit endpoints_compatible region:us conversational

Related

Total size
7.12 GB
Files
3
Quantizations
2
Registered
2026-08-22 13:56
Last updated on HF
2024-05-06 06:36

Files by quantization

F16 1 file 7.12 GB
ggml-model-f16.gguf 7.12 GB 606e0d85 download
Auxiliary files 2 files 1.56 KB
.gitattributes 1.54 KB a4cc060e download
README.md 24.0 B 7be5fc7f download

README current version from Hugging Face


license: mit

README history 1 version

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

  1. 2024-05-06initial commitd14c92421 B
    Loading...

Discussions 1 thread

  1. 2024-05-16Any plans to do the 128k version?open1 💬#1
    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