← back to catalog · registered 2026-09-13 15:56

SOMEHOTMEAL/Qwen3-14B-Janus-Abliterated-GGUF

SOMEHOTMEAL 14B GGUF
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

Applied on top of direct removal inherited from the base model.
Confidence
MEDIUM
Inherited from base model
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=1
  • assume M1 (base ablation) + M8 (GGUF quant) - default when producer unknown
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
2
Model age
today
created 2026-09-13

Metadata

Quantizations
Q4_K
Tags
gguf endpoints_compatible region:us conversational

Related

Total size
67.2 GB
Files
6
Quantizations
2
Registered
2026-09-13 15:56
Last updated on HF
2026-09-13 15:54

Files by quantization

Q4_K 1 file 8.38 GB
Qwen3-14B-Janus-Abliterated-v1-Q4_K_M-GGUF.gguf 8.38 GB f99be024 download
Auxiliary files 5 files 58.8 GB
Qwen3-14B-Janus-Abliterated-v1-f16-GGUF.gguf 27.5 GB 6edd6417 download
Qwen3-14B-Janus-Abliterated-v1-Q8_0-GGUF.gguf 14.6 GB 7a2ede8a download
Qwen3-14B-Janus-Abliterated-v1-Q6_K-GGUF.gguf 11.3 GB b9079dea download
Qwen3-14B-Janus-Abliterated-v1-Q2_K-GGUF.gguf 5.36 GB 0b166363 download
.gitattributes 1.88 KB a408a45d 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 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.