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

wisent-ai/Qwen3-8B-abliterated

wisent-ai Qwen 8.2B
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/wisent-ai%2FQwen3-8B-abliterated"
Response includes
  • classification m1
  • files 16
  • hub_downloads_all_time 40
  • author_summary 3 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

No other method signals detected in this model.
Confidence
MEDIUM
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=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
Downloads · lifetime
40
8 last 30d - stable
Likes
0
Model age
10mo ago
created 2025-11-26
Downloads over time
Now41→from18↑128%
1726344318 on Nov 26, 202541 on Oct 1141 on Oct 6Nov '25JanMarMayJulSep
Nov 26, 2025 → Oct 11 · 85 snapshots · spans 319 days

Metadata

Tags
safetensors qwen3 region:us

Related

Total size
15.3 GB
Files
16
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-11-27 04:18

Files by quantization

Auxiliary files 16 files 15.3 GB
model-00003-of-00004.safetensors 4.64 GB dbaf80cf download
model-00002-of-00004.safetensors 4.58 GB 70691958 download
model-00001-of-00004.safetensors 4.57 GB 17fc9389 download
model-00004-of-00004.safetensors 1.47 GB 93647b58 download
tokenizer.json 10.9 MB 1574cf58 download
vocab.json 2.65 MB 4783fe10 download
merges.txt 1.59 MB 31349551 download
model.safetensors.index.json 32.1 KB 991332e2 download
tokenizer_config.json 5.28 KB ddaf6980 download
chat_template.jinja 4.07 KB 01be9b30 download
.gitattributes 1.53 KB 52373fe2 download
config.json 1.50 KB 36431e69 download
added_tokens.json 707 B b54f9135 download
special_tokens_map.json 613 B ac23c0aa download
trial_info.txt 395 B 705ffa96 download
generation_config.json 214 B 9e289a1a download

README

The author did not publish a README.

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