Get the app
← back to catalog · registered 2026-09-11 19:55

Phil2Sat/Qwen-3.8-27B-Uncensored-I-Compact-GGUF

Phil2Sat Qwen 27B GGUF second-order
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
How we label → About M-U →
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
2K
↑ 0% in 90 days
Likes
2
Model age
3w ago
created 2026-08-15
Downloads over time
Now1.6K→from1.6K↑0%
1.6K1.6K1.6K1.6K1.6K on Sep 111.6K on Sep 12Sep
Sep 11 → Sep 12 · 2 snapshots · spans 1 day

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

Zynerji/Ektome-Qwen3.8-27B-PristinelyUncensored this lineage
Phil2Sat/Qwen-3.8-27B-Uncensored-I-Compact-GGUF↓ 1,628

Metadata

Tags
gguf base_model:Zynerji/Ektome-Qwen3.8-27B-PristinelyUncensored base_model:quantized:Zynerji/Ektome-Qwen3.8-27B-PristinelyUncensored endpoints_compatible region:us imatrix conversational

Related

Other by Phil2Sat
Qwen-3.8-27B-Uncensored-I-Compact.gguf_ALPHA_TESTING 2K Ornith-1.0-35B-AEON-Ultimate-Uncensored-MTP-APEX-I-Compact.gguf 308 Ornith-1.0-35B-AEON-Ultimate-Uncensored-MTP-APEX-I-Compact-GGUF 308
Same base model
Phil2Sat/Qwen-3.8-27B-Uncensored-I-Compact.gguf_ALPHA_TESTING 2K
Total size
13.9 GB
Files
3
Quantizations
1
Registered
2026-09-11 19:55
Last updated on HF
2026-08-15 08:43
Source huggingface.co/Phil2Sat/Qwen-3.8-27B-Uncensored-I-Compact-GGUF ↗ Base model Zynerji/Ektome-Qwen3.8-27B-PristinelyUncensored ↗

Files by quantization

Auxiliary files 3 files 13.9 GB
Qwen-3.8-27B-Uncensored-I-Compact-MXFP4.gguf 13.9 GB f4c29ab5 download
.gitattributes 1.64 KB 2584847d download
README.md 288 B 4c19c330 download

README current version from Hugging Face

base_model:

  • Zynerji/Ektome-Qwen3.8-27B-PristinelyUncensored

Frankenquant of Ektome-Qwen3.8-27B-PristinelyUncensored.

Goal is to fit into 16GB Vram, did my best, dunnow what im doin, pre alpha, but works so far.

MTP is included.

My first tests shows no refusals at all in RP.

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.

See supported apps Browse the catalog