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

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

mradermacher 27B GGUF 262K 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/mradermacher%2FSwift-Qwen3.8-27B-Abliterated-GGUF"
Response includes
  • classification m8
  • files 5
  • hub_downloads_all_time 13,184
  • author_summary 3467 models
  • readme_text full
Try next
GET/models?author=mradermacher
All 3467 models by mradermacher
 GET/methods/m8
What "m8" means · taxonomy
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
How we label → About M8 →
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
13K
1K last 30d - cooling
Likes
0
Model age
6w ago
created 2026-09-20
Downloads over time
Now14.8K→from0↑0%
05.4K10.9K16.3K0 on Sep 2014.8K on Nov 4SepOctNov
Sep 20 → Nov 4 · 46 snapshots · spans 45 days

Variants by this author 2 formats · 2K 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

Other by mradermacher
Ornith-1.5-9B-uncensored-GGUF 1.7M Qwen3-VL-8B-Instruct-abliterated-GGUF 669K Huihui-Qwen3.5-9B-abliterated-GGUF 324K Qwen3.8-Flash-Next-Uncensored-i1-GGUF 171K Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated-i1-GGUF 124K
Total size
10.1 GB
Files
5
Quantizations
4
Registered
2026-09-20 15:56
Last updated on HF
2026-09-20 17:20
Source huggingface.co/mradermacher/Swift-Qwen3.8-27B-Abliterated-GGUF ↗

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

README history 4 versions

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

  1. 2026-09-20auto-patch README.mdbf380144.2 KB
    Loading...
  2. 2026-09-20auto-patch README.mdd48f5e84 KB
    Loading...
  3. 2026-09-20auto-patch README.md407bec83.1 KB
    Loading...
  4. 2026-09-20uploaded from rich1a5dcc58383 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.

Get the app Browse the catalog
Open in Abliteration