← back to catalog · registered 2026-09-20 15:56

mradermacher/Swift-Qwen3.8-27B-Abliterated-GGUF

mradermacher 27B GGUF
curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/mradermacher%2FSwift-Qwen3.8-27B-Abliterated-GGUF"
Response includes
  • classification m8
  • files 5
  • author_summary 3247 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)

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 2 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.
  • author=mradermacher (M8 quantization producer)
  • is_gguf=1
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
0
Likes
0
Model age
today
created 2026-09-20

Variants by this author 2 formats · 0 downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

Quantizations
Q2_K
Tags
transformers gguf qwen3_8 qwen3_5 abliterated refusal-reduced reasoning vision-language en base_model:andrewting/Swift-Qwen3.8-27B-Abliterated base_model:quantized:andrewting/Swift-Qwen3.8-27B-Abliterated license:other

Related

Total size
10.1 GB
Files
5
Quantizations
4
Registered
2026-09-20 15:56
Last updated on HF
2026-09-20 16:54

Files by quantization

Q2_K 1 file 10.1 GB
Swift-Qwen3.8-27B-Abliterated.Q2_K.gguf 10.1 GB d1a3615c download
F16 1 file 885 MB
Swift-Qwen3.8-27B-Abliterated.mmproj-f16.gguf 885 MB 2cd8d9bd download
Q8_0 1 file 600 MB
Swift-Qwen3.8-27B-Abliterated.mmproj-Q8_0.gguf 600 MB 87971a9c download
Auxiliary files 2 files 2.09 KB
.gitattributes 1.72 KB 82b0a21a download
README.md 383 B 438c2c05 download

README current version from Hugging Face

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 - Abliteration, LM Studio, or Ollama. No API keys, no subscription, no prompt leakage.