← back to catalog · registered 2026-09-11 11:55

apetersson/Qwen3.8-Flash-Next-Abliterated

apetersson 262K ctx
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
109
Likes
0
Model age
5d ago
created 2026-09-11
Downloads over time
Now109from0↑0%
040801200 on Sep 11109 on Sep 16Sep
Sep 11 → Sep 16 · 6 snapshots · spans 5 days

Metadata

Tags
gguf llama.cpp qwen abliterated uncensored refusal-removal vision video image-text-to-text base_model:Qwen/Qwen3.8-Flash-Next base_model:quantized:Qwen/Qwen3.8-Flash-Next license:other

Related

Total size
0 B
Files
1
Quantizations
1
Registered
2026-09-11 11:55
Last updated on HF
2026-09-11 16:54

Files by quantization

Auxiliary files 1 file 1.48 KB
.gitattributes 1.48 KB a6344aac download

README

The author did not publish a README.

README history 4 versions

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

  1. 2026-09-11docs: remove duplicated model card sections89bb1c910.5 KB
    Loading...
  2. 2026-09-11docs: highlight measured capability resultsb1d1fef13.2 KB
    Loading...
  3. 2026-09-11Upload folder using huggingface_hubd17002211.8 KB
    Loading...
  4. 2026-09-11Upload folder using huggingface_hub66c259c10.3 KB
    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 app" button that hands off directly to a local runtime of your choice - Infrahuman, LM Studio, or Ollama. No API keys, no subscription, no prompt leakage.