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

ikarius/Qwen2.5-3B-Instruct-Abliterated-GGUF

ikarius Qwen 3B GGUF 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/ikarius%2FQwen2.5-3B-Instruct-Abliterated-GGUF"
Response includes
  • classification m8
  • files 4
  • hub_downloads_all_time 1,597
  • author_summary 17 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
2K
36 last 30d - cooling
Likes
0
Model age
10mo ago
created 2025-12-09
Downloads over time
Now1.6K→from49↑3,194%
05901.2K1.8K49 on Dec 10, 20251.6K on Oct 11Dec '25FebAprJunAugOct
Dec 10, 2025 → Oct 11 · 83 snapshots · spans 305 days

Metadata

License
apache-2.0
Quantizations
Q4_K Q8_0
Tags
gguf license:apache-2.0 endpoints_compatible region:us conversational

Related

Total size
4.86 GB
Files
4
Quantizations
3
Registered
2026-08-22 13:56
Last updated on HF
2025-12-09 05:25

Files by quantization

Q8_0 1 file 3.06 GB
huihui-ai.Qwen2.5-3B-Instruct-abliterated-SFT.Q8_0.gguf 3.06 GB 085cf370 download
Q4_K 1 file 1.80 GB
huihui-ai.Qwen2.5-3B-Instruct-abliterated-SFT.Q4_K_M.gguf 1.80 GB 5223c578 download
Auxiliary files 2 files 1.70 KB
.gitattributes 1.67 KB 4d73dc8b download
README.md 31.0 B 7b95401d download

README current version from Hugging Face


license: apache-2.0

README history 1 version

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

  1. 2025-12-09initial commitf6fdb2328 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